Models / MiniMax M3.1 Flash

MiniMax

MiniMax M3.1 Flash

MiniMax M3.1 Flash is best for reasoning and knowledge, and agents and tool use; a strong pick at a modest price. The cheapest model of similar intelligence is Claude Haiku 5.5, at $0.20 per million tokens against $0.26.

Results 19 Nov 2026 · 167 results · 6 sources

Price per million tokens
$0.15 in · $0.60 out
MiniMax's list price, 10 Nov 2026 · compare prices$0.01 cached input
Speed
159 tokens a second; on its test prompt the answer starts after 13.3 s, thinking time included
Artificial Analysis, on its usual API
Intelligence Index
42.4
Artificial Analysis
Spring Prompt overall
25th of 39 score 40 of 100 · how it works
Spring Prompt Score
37 of 100 25th of 35 · 5 of 5 benchmarks · our own tests only
Developer
MiniMax, based in China
Weights published
Released
19 Oct 2026
1,048,576 tokens of context
Pricing and availability
Flat rate, from MiniMax's launch post; on 19 Oct OpenRouter only offered a free route

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 21st of 185Claude Opus 5.5 25th of 38Claude Fable 5.2 $0.26 blended, 23rd percentilecheapest: Mistral Nemo 18th of 65Nemotron 3.5 Super VL
Models priced $0.25–1 per million tokens 3rd of 61MiMo-V2.6-Pro 2nd of 5DeepSeek-V4.1-Flash sets this group 9th of 20Gemini 3.5 Flash-Lite
Models with similar intelligence sets this group 5th of 10Gemini 3.8 Flash $0.26 blended, 9th percentilecheapest: Claude Haiku 5.5 4th of 15DeepSeek-V4.1-Flash
Models writing 100–200 tokens a second 3rd of 21Claude Sonnet 5.5 5th of 7Muse Wonder $0.26 blended, 15th percentilecheapest: Qwen3.5-9B sets this group
Models from developers based in China 6th of 75MiMo-V2.6-Pro 6th of 11Kimi K3.1 Pro $0.26 blended, 20th percentilecheapest: Qwen3.5-9B 4th of 23DeepSeek-V4.1-Flash
Open-weights models 5th of 104MiMo-V2.6-Pro 4th of 8Kimi K3.1 Pro $0.26 blended, 34th percentilecheapest: Mistral Nemo 13th of 43Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

Measured cost per task

API cost recorded in our benchmark runs, excluding judging.

TaskBenchmarkCost per task
Product listingCatalogBench≈ $0.001
DeckDeckBench≈ $0.010
Survey plan and analysisSurveyBench≈ $0.020
Game of bullet chessBulletBench≈ $0.002

Cheapest model that passes

On our benchmarks that define a pass for each task: what one passing answer cost in our run, failed attempts included, and whether a cheaper model passed.

  • CatalogBench · cost per 1,000 accepted listings
    MiniMax M3.1 Flash passed 106 of 168 attempts, with no estimate: no matching cost record. Cheapest: GPT-6 Luna at $0.70 (114 of 168 attempts).
  • DeckBench · cost per presentable deck
    MiniMax M3.1 Flash: no presentable decks (0 of 6 tasks). Cheapest: GPT-6.2 Sol at $0.09 (5 of 6 tasks).
  • SurveyBench · cost per sound survey task
    MiniMax M3.1 Flash: no sound survey tasks (0 of 9 tasks). Cheapest: GPT-6 Luna at $0.03 (3 of 9 tasks).

Cost per attempt divided by the share that passed, at the run date's prices, excluding judging. Each model at its cheapest setting per passing answer. With a handful of tasks, a pass or two either way is within chance. No estimate where a run had missing outputs, because their cost may not have been recorded.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $0.25–1 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live 14th of 35 available · 1st of 5 at its price
BenchmarkMiniMax M3.1 FlashRank among availableBest available
CatalogBenchCatalogBench: reliably publish-ready 50.0% 17th of 35 Gemini 4 Neon 78.6%
CatalogBenchCatalogBench (sales brief): reliably publish-ready 37.5% 10th of 35 GPT-6.2 Sol 75.0%
Decks from an analysisTurning a finished analysis into a deck you could present as it is 10th of 35 available · 1st of 4 at its price
BenchmarkMiniMax M3.1 FlashRank among availableBest available
DeckBenchDeckBench: deck rating 1,266 10th of 35 Qwen4-Max 1,563
User surveysPlanning a user survey and reading its results without being misled 26th of 26 available · 4th of 4 at its price
BenchmarkMiniMax M3.1 FlashRank among availableBest available
SurveyBenchSurveyBench: analysis rating 428 26th of 26 Claude Fable 5.2 1,670
Marketing planningPlanning a year of ad spend without overspending 24th of 35 available · 3rd of 4 at its price
BenchmarkMiniMax M3.1 FlashRank among availableBest available
ROASBenchROASBench: overall score 40.3 24th of 35 Claude Fable 5.2 61.3
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 33rd of 159 available · 4th of 47 at its price
BenchmarkMiniMax M3.1 FlashRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 25.8% 23rd of 107 Kimi K3.1 Pro 67.2%
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
  • Vending-Bench 2: pending. Its latest results are dated 1 Oct 2026, before this model was released.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects PendingReleased after these sources last updated
  • APEX-Agents: pending. Its latest results are dated 1 Oct 2026, before this model was released.
  • GDP.pdf: pending. Its latest results are dated 1 Oct 2026, before this model was released.
  • Remote Labor Index: pending. Its latest results are dated 1 Oct 2026, before this model was released.
Reasoning and knowledgeHard questions across science, maths and general knowledge 19th of 187 available · 2nd of 61 at its price
BenchmarkMiniMax M3.1 FlashRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 42.4 21st of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 48.0% 15th of 186 Claude Opus 5.5 61.4%
WritingWhat people prefer in blind comparisons, and judged writing quality PendingReleased after these sources last updated
  • Arena (formerly LMArena): pending. Its latest results are dated 2 Oct 2026, before this model was released.
  • UGI Leaderboard: pending. Its latest results are dated 2 Oct 2026, before this model was released.
Sticking to the factsSummarising without inventing things, and factual answers PendingReleased after these sources last updated
  • Vectara Hallucination Leaderboard: pending. Its latest results are dated 22 Sep 2026, before this model was released.
  • Arena (formerly LMArena): pending. Its latest results are dated 2 Oct 2026, before this model was released.
  • SimpleQA Verified (Epoch AI): pending. Its latest results are dated 29 Sep 2026, before this model was released.
Speed under pressureGood decisions against a real clock (fast chess) 34th of 38 available · 8th of 8 at its price
BenchmarkMiniMax M3.1 FlashRank among availableBest available
BulletBenchBulletBench Bullet 60s: ladder Elo 115 32nd of 36 Gemini 3.8 Flash 1,068

Nearest alternatives

Against MiniMax M3.1 Flash at $0.26 blended, Intelligence Index 42.4. "Similar intelligence" means within 4 points or better.

Where to run it

13 hosts on OpenRouter at the standard service tier, with a median of $0.26 blended per million tokens; quantisation where the host states it: FP8, FP4, FP16. Cheapest first.

HostQuantisationInputOutputBlended
GMICloudFP8$0.11$0.45$0.20
StreamLakeFP8$0.14$0.54$0.24
DigitalOceannot stated$0.15$0.60$0.26
Fireworksnot stated$0.15$0.60$0.26
InferenceNetFP4$0.15$0.60$0.26
InferenceNetFP4$0.15$0.60$0.26
Minimaxnot stated$0.15$0.60$0.26
ModelRunFP4$0.15$0.60$0.26

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 5 dearer hosts are left out.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

MiniMax M3.1 FlashMiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
Claude Haiku 5.5
cheapest with similar intelligence
DeepSeek-V4.1-Flash
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.26 $0.54$0.20$0.52$8.00
Tokens a second 159 4324036996
Intelligence Index 42.4 46.343.439.557.6
Spring Prompt overall 40 –384980
Rank among available models, by use case
Product listings 14th of 35 –23rd18th16th
Decks from an analysis 10th of 35 –19th–8th
User surveys 26th of 26 –9th–5th
Marketing planning 24th of 35 –33rd–11th
Agents and tool use 33rd of 159 23rd28th31st3rd
Professional work pending –––3rd
Reasoning and knowledge 19th of 187 13th25th42nd1st
Writing pending 23rd–29th5th
Sticking to the facts pending 10th–23rd3rd
Speed under pressure 34th of 38 –24th––

Shaded figures are better than MiniMax M3.1 Flash's. A dash means no result.

Research and examples

In the playground: our pick in 0 of 29 tests, 76% of checks passed →

Where it has been measured

3rd most intelligent of the 61 models priced $0.25–1 per million tokens, and 3rd cheapest of the 23 models with similar intelligence. Among models available today, in the top quarter (by percentile) for reasoning and knowledge, and agents and tool use; in the bottom quarter for user surveys and speed under pressure. Results for professional work, writing and sticking to the facts are pending: those sources last updated before this model was released.

Every result

167 published results from 6 sources, each in the source's own units, with the configuration that produced it.

BulletBench · measured by Spring Prompt · 5 results
MeasureValueRankConfigurationDated
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0016 20 of 76 MiniMax M3.1 Flash (low reasoning)
low reasoning
4 Nov 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 75.0% 59 of 76 MiniMax M3.1 Flash (low reasoning)
low reasoning
4 Nov 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.0% 1 of 76 MiniMax M3.1 Flash (low reasoning)
low reasoning
4 Nov 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 115
0–485
70 of 76 MiniMax M3.1 Flash (low reasoning)
low reasoning
4 Nov 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 3.0 s 63 of 76 MiniMax M3.1 Flash (low reasoning)
low reasoning
4 Nov 2026

Not shown: Not your cost: prices are those charged on the run date.

CatalogBench · measured by Spring Prompt · 62 results
MeasureValueRankConfigurationDated
CatalogBench (sales brief): channel rules broken% of products, lower is better 1.2% 28 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): channel rules broken% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): claims to check% of products, lower is better 0.0% 1 of 35 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): content quality% of checks, higher is better 96.3% 24 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): content quality% of checks, higher is better 96.0% 28 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): failed outputs% of products, lower is better 1.2% 31 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): failed outputs% of products, lower is better 1.8% 34 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): missing UK information% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): missing UK information% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): not findable% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): not findable% of products, lower is better 4.2% 21 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): publish-ready listings% of products, higher is better 0.0% 35 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): publish-ready listings% of products, higher is better 57.1% 12 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): reliably publish-ready% of products, higher is better 0.0% 30 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): reliably publish-ready% of products, higher is better 37.5% 10 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): unsupported claims% of products, lower is better 15.5% 9 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): unsupported claims% of products, lower is better 16.1% 10 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): unsupported claimsclaims per product, lower is better 0.64 12 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): unsupported claimsclaims per product, lower is better 0.60 11 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): wrong attributes% of products, lower is better 21.4% 30 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): wrong attributes% of products, lower is better 21.4% 30 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench (sales brief): wrong category or variant% of products, lower is better 6.0% 35 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench (sales brief): wrong category or variant% of products, lower is better 4.8% 33 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: channel compliance% of products, higher is better 100.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: channel compliance% of products, higher is better 100.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: channel rules broken% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: channel rules broken% of products, lower is better 0.6% 22 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: claims to check% of products, lower is better 0.0% 1 of 35 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: conflicts caught% of conflicts, higher is better 100.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: conflicts caught% of conflicts, higher is better 100.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: content quality% of checks, higher is better 96.2% 27 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: content quality% of checks, higher is better 95.8% 29 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: cost per productUS dollars, lower is better $0.0010 3 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: cost per productUS dollars, lower is better $0 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: decision accuracy% of decisions, higher is better 96.1% 24 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: decision accuracy% of decisions, higher is better 95.6% 28 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: failed outputs% of products, lower is better 1.2% 31 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: failed outputs% of products, lower is better 1.8% 33 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: field accuracy% of missing fields, higher is better 92.7% 27 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: field accuracy% of missing fields, higher is better 92.0% 32 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: invented values% of filled values, lower is better 4.5% 36 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: invented values% of filled values, lower is better 3.8% 34 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: missing UK information% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: missing UK information% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: not findable% of products, lower is better 0.0% 1 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: not findable% of products, lower is better 7.1% 28 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: output tokens per producttokens, lower is better 3,014 11 of 15 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: output tokens per producttokens, lower is better 2,890 10 of 15 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: publish-ready listings% of products, higher is better 0.0% 36 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: publish-ready listings% of products, higher is better 63.1% 20 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: reliably publish-ready% of products, higher is better 0.0% 35 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: reliably publish-ready% of products, higher is better 50.0% 17 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: time per productseconds, lower is better 25.2 27 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: time per productseconds, lower is better 32.0 29 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: unsupported claims% of products, lower is better 8.3% 13 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: unsupported claims% of products, lower is better 7.7% 12 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: unsupported claimsclaims per product, lower is better 0.41 16 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: unsupported claimsclaims per product, lower is better 0.39 15 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: wrong attributes% of products, lower is better 22.6% 32 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: wrong attributes% of products, lower is better 22.6% 32 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
CatalogBench: wrong category or variant% of products, lower is better 2.4% 23 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
CatalogBench: wrong category or variant% of products, lower is better 4.2% 32 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026

Not shown: Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.

DeckBench · measured by Spring Prompt · 36 results
MeasureValueRankConfigurationDated
DeckBench: accurate decks% of tasks, higher is better 83.3% 6 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: accurate decks% of tasks, higher is better 50.0% 17 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: caveat dropped% of tasks, lower is better 16.7% 16 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: caveat dropped% of tasks, lower is better 33.3% 34 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: clean layout% of tasks, higher is better 0.0% 31 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: clean layout% of tasks, higher is better 0.0% 31 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: cost per deckUS dollars, lower is better $0.0104 5 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: cost per deckUS dollars, lower is better $0 1 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: deck ratingrating, higher is better 1,266
1,177–1,367
10 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: deck ratingrating, higher is better 1,043
950–1,135
23 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: design quality% of the maximum, higher is better 66.9% 19 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: design quality% of the maximum, higher is better 46.2% 33 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: draft figure quoted% of tasks, lower is better 0.0% 1 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: draft figure quoted% of tasks, lower is better 33.3% 21 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: findings missing% of tasks, lower is better 0.0% 1 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: findings missing% of tasks, lower is better 50.0% 36 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: head-to-head win rate% of comparisons, higher is better 63.9% 14 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: head-to-head win rate% of comparisons, higher is better 45.5% 23 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: layout defects% of tasks, lower is better 100.0% 31 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: layout defects% of tasks, lower is better 100.0% 31 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: misleading metric used% of tasks, lower is better 0.0% 1 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: misleading metric used% of tasks, lower is better 33.3% 35 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: output tokens per decktokens, lower is better 33,765 12 of 16 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: output tokens per decktokens, lower is better 45,141 14 of 16 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: presentable decks% of tasks, higher is better 0.0% 17 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: presentable decks% of tasks, higher is better 0.0% 17 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: recommendation late or wrong% of tasks, lower is better 0.0% 1 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: recommendation late or wrong% of tasks, lower is better 33.3% 22 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: slides needing work% of tasks, lower is better 50.0% 19 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: slides needing work% of tasks, lower is better 83.3% 34 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: time per deckseconds, lower is better 217 26 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: time per deckseconds, lower is better 330 30 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: unsupported claims% of tasks, lower is better 0.0% 1 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: unsupported claims% of tasks, lower is better 50.0% 32 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
DeckBench: unsupported numbers% of tasks, lower is better 0.0% 1 of 37 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
DeckBench: unsupported numbers% of tasks, lower is better 50.0% 35 of 37 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026

Not shown: Not your analysis or your brand: invented companies, six public tasks, one deck per model per task at the provider's default reasoning setting.

ROASBench · measured by Spring Prompt · 18 results
MeasureValueRankConfigurationDated
ROASBench: audience scorescore out of 100, higher is better 60.2 24 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: audience scorescore out of 100, higher is better 60.8 22 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: business scorescore out of 100, higher is better 31.9 27 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: business scorescore out of 100, higher is better 38.9 22 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: consistency scorescore out of 100, higher is better 14.9 32 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: consistency scorescore out of 100, higher is better 17.3 29 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: contribution profitsimulated US dollars, higher is better $539,202 23 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: contribution profitsimulated US dollars, higher is better $693,379 13 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: cost of a runUS dollars, lower is better $0.0379 7 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: cost of a runUS dollars, lower is better $0 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: months over budgetmonths of 12, lower is better 1 33 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: months over budgetmonths of 12, lower is better 0 1 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: overall scorescore out of 100, higher is better 36.3 28 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: overall scorescore out of 100, higher is better 40.3 24 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: planning scorescore out of 100, higher is better 54.4 28 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: planning scorescore out of 100, higher is better 54.2 32 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
ROASBench: return on ad spendprofit per $1 spent, higher is better $0.43 25 of 38 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
ROASBench: return on ad spendprofit per $1 spent, higher is better $0.52 19 of 38 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026

Not shown: Not real ad performance: the market is a deterministic simulation of one invented skincare brand.

SurveyBench · measured by Spring Prompt · 39 results
MeasureValueRankConfigurationDated
SurveyBench: analysis ratingrating, higher is better 428
220–567
27 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: analysis ratingrating, higher is better 422
239–529
28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: analysis scorepoints of 100, higher is better 13.6 27 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: analysis scorepoints of 100, higher is better 7.90 28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: cost per taskUS dollars, lower is better $0.0198 5 of 27 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: head-to-head win rate% of comparisons, higher is better 20.3% 27 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: head-to-head win rate% of comparisons, higher is better 14.9% 28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: leading or double-barrelled questions% of tasks, lower is better 44.4% 15 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: leading or double-barrelled questions% of tasks, lower is better 77.8% 27 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: mistaken next steps% of tasks, lower is better 77.8% 24 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: mistaken next steps% of tasks, lower is better 100.0% 28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: numbers right% of answers, higher is better 90.9% 24 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: numbers right% of answers, higher is better 100.0% 1 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: objectives unanswerable% of tasks, lower is better 44.4% 27 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: objectives unanswerable% of tasks, lower is better 66.7% 28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: output tokens per tasktokens, lower is better 63,237 16 of 17 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: precision ignored% of tasks, lower is better 44.4% 21 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: precision ignored% of tasks, lower is better 66.7% 25 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: research scorepoints of 100, higher is better 28.3 27 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: research scorepoints of 100, higher is better 16.4 28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: sound research% of tasks, higher is better 0.0% 17 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: sound research% of tasks, higher is better 0.0% 17 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: stakeholder's view presumed% of tasks, lower is better 33.3% 25 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: stakeholder's view presumed% of tasks, lower is better 55.6% 27 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: survey plan scorepoints of 100, higher is better 62.5 26 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: survey plan scorepoints of 100, higher is better 36.1 28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: survey structure% of tasks, lower is better 44.4% 25 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: survey structure% of tasks, lower is better 77.8% 28 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: time per taskseconds, lower is better 352 21 of 27 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: traps handled% of traps, higher is better 66.7% 24 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: traps handled% of traps, higher is better 75.0% 22 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: traps missed% of tasks, lower is better 88.9% 19 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: traps missed% of tasks, lower is better 100.0% 25 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: unsupported findings% of tasks, lower is better 88.9% 22 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: unsupported findings% of tasks, lower is better 100.0% 24 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: wrong numbers% of tasks, lower is better 100.0% 25 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: wrong numbers% of tasks, lower is better 88.9% 24 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026
SurveyBench: wrong recommendation% of tasks, lower is better 88.9% 25 of 28 MiniMax M3.1 Flash
provider default reasoning
4 Nov 2026
SurveyBench: wrong recommendation% of tasks, lower is better 100.0% 27 of 28 MiniMax M3.1 Flash
provider default reasoning
19 Oct 2026

Not shown: Not your customers or your data: invented organisations with simulated respondents, nine public tasks, one run per model per task at the provider's default reasoning setting.

Artificial Analysis · reported by Artificial Analysis · 7 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 42.4 46 of 413 MiniMax M3.1 Flash 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 48.0% 34 of 419 MiniMax M3.1 Flash 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 79.7% 86 of 407 MiniMax M3.1 Flash 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 159 31 of 137 MiniMax M3.1 Flash 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 53.4% 75 of 205 MiniMax M3.1 Flash 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 25.8% 56 of 204 MiniMax M3.1 Flash 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 13.3 67 of 137 MiniMax M3.1 Flash 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

Embed a score badge

A badge for its Spring Prompt Score and each of our benchmarks that ranked MiniMax M3.1 Flash, from the current results. Paste the code into a page or README; it links back to where the result comes from.

MiniMax M3.1 Flash is #25 of 35 on the Spring Prompt Score (37 of 100, from 5 of 5 of our benchmarks), measured by Spring Prompt Spring Prompt Score · 5 of 5 benchmarks
<a href="https://springprompt.com/score#minimax-minimax-m3-1-flash"><img src="https://springprompt.com/badge/score/minimax-minimax-m3-1-flash.svg" alt="MiniMax M3.1 Flash is #25 of 35 on the Spring Prompt Score (37 of 100, from 5 of 5 of our benchmarks), measured by Spring Prompt" height="20"></a>
MiniMax M3.1 Flash is #17 of 35 on CatalogBench (Reliably publish-ready, factual brief: 50.0%), measured by Spring Prompt CatalogBench · Reliably publish-ready, factual brief
<a href="https://springprompt.com/benchmarks/catalogbench?focus=minimax-minimax-m3-1-flash"><img src="https://springprompt.com/badge/catalogbench/minimax-minimax-m3-1-flash.svg" alt="MiniMax M3.1 Flash is #17 of 35 on CatalogBench (Reliably publish-ready, factual brief: 50.0%), measured by Spring Prompt" height="20"></a>
MiniMax M3.1 Flash is #10 of 36 on DeckBench (Deck rating: 1,266), measured by Spring Prompt DeckBench · Deck rating
<a href="https://springprompt.com/benchmarks/deckbench?focus=minimax-minimax-m3-1-flash"><img src="https://springprompt.com/badge/deckbench/minimax-minimax-m3-1-flash.svg" alt="MiniMax M3.1 Flash is #10 of 36 on DeckBench (Deck rating: 1,266), measured by Spring Prompt" height="20"></a>
MiniMax M3.1 Flash is #27 of 27 on SurveyBench (Analysis rating: 428), measured by Spring Prompt SurveyBench · Analysis rating
<a href="https://springprompt.com/benchmarks/surveybench?focus=minimax-minimax-m3-1-flash"><img src="https://springprompt.com/badge/surveybench/minimax-minimax-m3-1-flash.svg" alt="MiniMax M3.1 Flash is #27 of 27 on SurveyBench (Analysis rating: 428), measured by Spring Prompt" height="20"></a>
MiniMax M3.1 Flash is #24 of 36 on ROASBench (Score: 40.3), measured by Spring Prompt ROASBench · Score
<a href="https://springprompt.com/benchmarks/roasbench?focus=minimax-minimax-m3-1-flash"><img src="https://springprompt.com/badge/roasbench/minimax-minimax-m3-1-flash.svg" alt="MiniMax M3.1 Flash is #24 of 36 on ROASBench (Score: 40.3), measured by Spring Prompt" height="20"></a>
MiniMax M3.1 Flash is #58 of 62 on BulletBench (Ladder Elo: 115), measured by Spring Prompt BulletBench · Ladder Elo
<a href="https://springprompt.com/benchmarks/bulletbench?focus=minimax-minimax-m3-1-flash"><img src="https://springprompt.com/badge/bulletbench/minimax-minimax-m3-1-flash.svg" alt="MiniMax M3.1 Flash is #58 of 62 on BulletBench (Ladder Elo: 115), measured by Spring Prompt" height="20"></a>

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.