Models / Gemini 4 Argon

Google

Gemini 4 Argon

Gemini 4 Argon is best for writing and sticking to the facts; pick it when quality matters more than cost.

Results 19 Nov 2026 · 103 results · 7 sources

Test Gemini 4 Argon on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$2.00 in · $10.00 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
52.6
Artificial Analysis, at high reasoning
Spring Prompt overall
8th of 39 score 70 of 100 · how it works
Spring Prompt Score
42 of 100 20th of 35 · 5 of 5 benchmarks · our own tests only
Developer
Google, based in the US
Weights not published
Released
13 Oct 2026
1,048,576 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 5th of 185Claude Opus 5.5 8th of 38Claude Fable 5.2 $4.00 blended, 82nd percentilecheapest: Mistral Nemo –
Models priced $3–10 per million tokens 3rd of 38Claude Opus 5.5 4th of 17GPT-6.2 Sol sets this group –
Models with similar intelligence sets this group 3rd of 6GPT-6.1 Sol $4.00 blended, 0th percentilecheapest: Claude Sonnet 5.5 –
Models from developers based in the US 5th of 92Claude Opus 5.5 8th of 24Claude Fable 5.2 $4.00 blended, 66th percentilecheapest: Gemma 3 4B –

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≈ $0.011
DeckDeckBench≈ $0.115
Survey plan and analysisSurveyBench≈ $0.131
Game of blitz chessBulletBench≈ $0.122

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
    Gemini 4 Argon: $15.42 (119 of 168 attempts), 11 of 27. Cheapest: GPT-6 Luna at $0.70 (114 of 168 attempts). Cheaper and passed at least as often: GPT-6.1 Terra at $4.78 (125 of 168 attempts).
  • DeckBench · cost per presentable deck
    Gemini 4 Argon: 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
    Gemini 4 Argon: 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 $3–10 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 15th of 35 available · 8th of 16 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
CatalogBenchCatalogBench: reliably publish-ready 60.7% 11th of 35 Gemini 4 Neon 78.6%
CatalogBenchCatalogBench (sales brief): reliably publish-ready 17.9% 17th of 35 GPT-6.2 Sol 75.0%
Decks from an analysisTurning a finished analysis into a deck you could present as it is 26th of 35 available · 14th of 17 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
DeckBenchDeckBench: deck rating 951 26th of 35 Qwen4-Max 1,563
User surveysPlanning a user survey and reading its results without being misled 17th of 26 available · 7th of 12 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
SurveyBenchSurveyBench: analysis rating 928 17th of 26 Claude Fable 5.2 1,670
Marketing planningPlanning a year of ad spend without overspending 15th of 35 available · 8th of 16 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
ROASBenchROASBench: overall score 47.0 15th of 35 Claude Fable 5.2 61.3
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 5th of 159 available · 4th of 35 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 57.1% 5th 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 4th of 187 available · 3rd of 39 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 52.6 5th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 57.1% 3rd of 186 Claude Opus 5.5 61.4%
WritingWhat people prefer in blind comparisons, and judged writing quality 1st of 169 available · 1st of 34 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,525 1st of 153 This model
  • 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 1st of 139 available · 1st of 31 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,511 1st of 109 This model
  • Vectara Hallucination Leaderboard: pending. Its latest results are dated 22 Sep 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) 29th of 38 available · 13th of 16 at its price
BenchmarkGemini 4 ArgonRank among availableBest available
BulletBenchBulletBench Bullet 60s: ladder Elo 147 28th of 36 Gemini 3.8 Flash 1,068

Nearest alternatives

Against Gemini 4 Argon at $4.00 blended, Intelligence Index 52.6. "Similar intelligence" means within 4 points or better.

Where to run it

3 hosts on OpenRouter at the standard service tier, with a median of $4.00 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Googlenot stated$2.00$10.00$4.00
Google AI Studionot stated$2.00$10.00$4.00
Googlenot stated$2.20$11.00$4.40

Other service tiers, not counted above: Google AI Studio flex $1.00 in, $5.00 out; Google priority $3.60 in, $18.00 out; Google AI Studio priority $3.60 in, $18.00 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

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

Scroll sideways to see every alternative.

Gemini 4 ArgonClaude Opus 5.5
most intelligent at $3–10 per million tokens
Claude Sonnet 5.5
cheapest with similar intelligence
GPT-6.2 Sol
highest-scoring overall at $3–10 per million tokens
Claude Fable 5.2
highest-scoring overall available today
Price per million tokens $4.00 $8.00$4.00$4.00$16.00
Tokens a second – 96137––
Intelligence Index 52.6 57.656.0––
Spring Prompt overall 70 80608488
Rank among available models, by use case
Product listings 15th of 35 16th21st1st8th
Decks from an analysis 26th of 35 8th7th6th4th
User surveys 17th of 26 5th–7th1st
Marketing planning 15th of 35 11th8th9th1st
Agents and tool use 5th of 159 3rd2nd––
Professional work pending 3rd1st––
Reasoning and knowledge 4th of 187 1st2nd––
Writing 1st of 169 5th33rd––
Sticking to the facts 1st of 139 3rd42nd––
Speed under pressure 29th of 38 –35th10th10th

Shaded figures are better than Gemini 4 Argon's. A dash means no result.

Research and examples

In the playground: our pick in 0 of 28 tests →

Where it has been measured

Cheapest of the 8 models with similar intelligence, and 3rd most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the top quarter (by percentile) for 4 of the 9 use cases measured, led by writing and sticking to the facts; in the bottom quarter for speed under pressure. Results for professional work are pending: those sources last updated before this model was released.

Artificial Analysis lists it but has not published a speed for it yet

Every result

103 published results from 7 sources, each in the source's own units, with the configuration that produced it.

BulletBench · measured by Spring Prompt · 10 results
MeasureValueRankConfigurationDated
BulletBench Blitz 3+2: cost per gameUS dollars, lower is better $0.12 14 of 25 Gemini 4 Argon
provider default reasoning
13 Oct 2026
BulletBench Blitz 3+2: games lost on time% of games, lower is better 0.0% 1 of 25 Gemini 4 Argon
provider default reasoning
13 Oct 2026
BulletBench Blitz 3+2: invalid moves% of moves, lower is better 0.0% 1 of 25 Gemini 4 Argon
provider default reasoning
13 Oct 2026
BulletBench Blitz 3+2: ladder Eloladder Elo, higher is better 1,147
979–1,373
1 of 25 Gemini 4 Argon
provider default reasoning
13 Oct 2026
BulletBench Blitz 3+2: median move timemilliseconds, lower is better 1.9 s 5 of 25 Gemini 4 Argon
provider default reasoning
13 Oct 2026
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0036 30 of 76 Gemini 4 Argon
provider default reasoning
14 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 87.5% 67 of 76 Gemini 4 Argon
provider default reasoning
14 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.0% 1 of 76 Gemini 4 Argon
provider default reasoning
14 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 147
0–381
63 of 76 Gemini 4 Argon
provider default reasoning
14 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 2.9 s 60 of 76 Gemini 4 Argon
provider default reasoning
14 Oct 2026

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

CatalogBench · measured by Spring Prompt · 31 results
MeasureValueRankConfigurationDated
CatalogBench (sales brief): channel rules broken% of products, lower is better 0.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): claims to check% of products, lower is better 0.0% 1 of 35 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): content quality% of checks, higher is better 98.4% 8 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): failed outputs% of products, lower is better 0.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): missing UK information% of products, lower is better 0.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): not findable% of products, lower is better 1.8% 5 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): publish-ready listings% of products, higher is better 35.1% 17 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): reliably publish-ready% of products, higher is better 17.9% 17 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): unsupported claims% of products, lower is better 63.1% 23 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): unsupported claimsclaims per product, lower is better 1.98 22 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): wrong attributes% of products, lower is better 15.5% 15 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench (sales brief): wrong category or variant% of products, lower is better 1.8% 7 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: channel compliance% of products, higher is better 100.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: channel rules broken% of products, lower is better 0.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: claims to check% of products, lower is better 0.0% 1 of 35 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: conflicts caught% of conflicts, higher is better 100.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: content quality% of checks, higher is better 98.2% 8 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: cost per productUS dollars, lower is better $0.0109 21 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: decision accuracy% of decisions, higher is better 97.8% 10 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: failed outputs% of products, lower is better 0.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: field accuracy% of missing fields, higher is better 94.7% 8 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: invented values% of filled values, lower is better 1.7% 21 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: missing UK information% of products, lower is better 0.0% 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: not findable% of products, lower is better 2.4% 9 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: publish-ready listings% of products, higher is better 70.8% 13 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: reliably publish-ready% of products, higher is better 60.7% 11 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: time per productseconds, lower is better 7.30 5 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: unsupported claims% of products, lower is better 16.1% 19 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: unsupported claimsclaims per product, lower is better 0.42 17 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: wrong attributes% of products, lower is better 15.5% 14 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
CatalogBench: wrong category or variant% of products, lower is better 1.8% 7 of 38 Gemini 4 Argon
provider default reasoning
13 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 · 17 results
MeasureValueRankConfigurationDated
DeckBench: accurate decks% of tasks, higher is better 33.3% 23 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: caveat dropped% of tasks, lower is better 0.0% 1 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: clean layout% of tasks, higher is better 33.3% 18 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: cost per deckUS dollars, lower is better $0.11 19 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: deck ratingrating, higher is better 951
883–1,025
27 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: design quality% of the maximum, higher is better 55.2% 28 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: draft figure quoted% of tasks, lower is better 50.0% 30 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: findings missing% of tasks, lower is better 0.0% 1 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: head-to-head win rate% of comparisons, higher is better 51.4% 19 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: layout defects% of tasks, lower is better 66.7% 18 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: misleading metric used% of tasks, lower is better 0.0% 1 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: presentable decks% of tasks, higher is better 0.0% 17 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: recommendation late or wrong% of tasks, lower is better 0.0% 1 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: slides needing work% of tasks, lower is better 66.7% 26 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: time per deckseconds, lower is better 67.5 8 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: unsupported claims% of tasks, lower is better 16.7% 17 of 37 Gemini 4 Argon
provider default reasoning
13 Oct 2026
DeckBench: unsupported numbers% of tasks, lower is better 0.0% 1 of 37 Gemini 4 Argon
provider default reasoning
13 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 · 9 results
MeasureValueRankConfigurationDated
ROASBench: audience scorescore out of 100, higher is better 65.5 16 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: business scorescore out of 100, higher is better 43.3 17 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: consistency scorescore out of 100, higher is better 34.7 11 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: contribution profitsimulated US dollars, higher is better $673,561 15 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: cost of a runUS dollars, lower is better $0.24 21 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: months over budgetmonths of 12, lower is better 0 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: overall scorescore out of 100, higher is better 47.0 15 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: planning scorescore out of 100, higher is better 55.4 1 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026
ROASBench: return on ad spendprofit per $1 spent, higher is better $0.55 16 of 38 Gemini 4 Argon
provider default reasoning
13 Oct 2026

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

SurveyBench · measured by Spring Prompt · 20 results
MeasureValueRankConfigurationDated
SurveyBench: analysis ratingrating, higher is better 928
863–989
17 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: analysis scorepoints of 100, higher is better 79.6 15 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: cost per taskUS dollars, lower is better $0.13 16 of 27 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: head-to-head win rate% of comparisons, higher is better 40.2% 19 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: leading or double-barrelled questions% of tasks, lower is better 66.7% 24 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: mistaken next steps% of tasks, lower is better 33.3% 18 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: numbers right% of answers, higher is better 97.1% 22 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: objectives unanswerable% of tasks, lower is better 0.0% 1 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: precision ignored% of tasks, lower is better 11.1% 16 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: research scorepoints of 100, higher is better 83.3 16 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: sound research% of tasks, higher is better 0.0% 17 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: stakeholder's view presumed% of tasks, lower is better 11.1% 12 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: survey plan scorepoints of 100, higher is better 91.8 17 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: survey structure% of tasks, lower is better 0.0% 1 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: time per taskseconds, lower is better 74.4 4 of 27 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: traps handled% of traps, higher is better 84.1% 18 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: traps missed% of tasks, lower is better 77.8% 17 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: unsupported findings% of tasks, lower is better 88.9% 22 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: wrong numbers% of tasks, lower is better 33.3% 19 of 28 Gemini 4 Argon
provider default reasoning
13 Oct 2026
SurveyBench: wrong recommendation% of tasks, lower is better 11.1% 5 of 28 Gemini 4 Argon
provider default reasoning
13 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.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better 0.15
0.12–0.18
3 of 50 Gemini 4 Argon (high reasoning, arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better 0.28
0.20–0.35
4 of 50 Gemini 4 Argon (high reasoning, arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better 0.13
0.12–0.15
1 of 50 Gemini 4 Argon (high reasoning, arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better 0.00
-0.00–0.00
31 of 50 Gemini 4 Argon (high reasoning, arena agent) 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,511
1,503–1,518
1 of 182 Gemini 4 Argon (high reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,522
1,502–1,543
1 of 406 Gemini 4 Argon (high reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,519
1,499–1,538
1 of 411 Gemini 4 Argon (high reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,539
1,513–1,565
7 of 363 Gemini 4 Argon (high reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,528
1,514–1,543
1 of 413 Gemini 4 Argon (high reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,525
1,516–1,534
1 of 413 Gemini 4 Argon (high reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,522
1,505–1,539
1 of 412 Gemini 4 Argon (high reasoning) 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 5 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 52.6 8 of 413 Gemini 4 Argon (high reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 57.1% 5 of 419 Gemini 4 Argon (high reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 79.7% 86 of 407 Gemini 4 Argon (high reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 61.8% 4 of 205 Gemini 4 Argon (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 57.1% 7 of 204 Gemini 4 Argon (high reasoning) 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 Gemini 4 Argon, from the current results. Paste the code into a page or README; it links back to where the result comes from.

Gemini 4 Argon is #20 of 35 on the Spring Prompt Score (42 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#google-gemini-4-argon"><img src="https://springprompt.com/badge/score/google-gemini-4-argon.svg" alt="Gemini 4 Argon is #20 of 35 on the Spring Prompt Score (42 of 100, from 5 of 5 of our benchmarks), measured by Spring Prompt" height="20"></a>
Gemini 4 Argon is #11 of 35 on CatalogBench (Reliably publish-ready, factual brief: 60.7%), measured by Spring Prompt CatalogBench · Reliably publish-ready, factual brief
<a href="https://springprompt.com/benchmarks/catalogbench?focus=google-gemini-4-argon"><img src="https://springprompt.com/badge/catalogbench/google-gemini-4-argon.svg" alt="Gemini 4 Argon is #11 of 35 on CatalogBench (Reliably publish-ready, factual brief: 60.7%), measured by Spring Prompt" height="20"></a>
Gemini 4 Argon is #26 of 36 on DeckBench (Deck rating: 951), measured by Spring Prompt DeckBench · Deck rating
<a href="https://springprompt.com/benchmarks/deckbench?focus=google-gemini-4-argon"><img src="https://springprompt.com/badge/deckbench/google-gemini-4-argon.svg" alt="Gemini 4 Argon is #26 of 36 on DeckBench (Deck rating: 951), measured by Spring Prompt" height="20"></a>
Gemini 4 Argon is #17 of 27 on SurveyBench (Analysis rating: 928), measured by Spring Prompt SurveyBench · Analysis rating
<a href="https://springprompt.com/benchmarks/surveybench?focus=google-gemini-4-argon"><img src="https://springprompt.com/badge/surveybench/google-gemini-4-argon.svg" alt="Gemini 4 Argon is #17 of 27 on SurveyBench (Analysis rating: 928), measured by Spring Prompt" height="20"></a>
Gemini 4 Argon is #15 of 36 on ROASBench (Score: 47.0), measured by Spring Prompt ROASBench · Score
<a href="https://springprompt.com/benchmarks/roasbench?focus=google-gemini-4-argon"><img src="https://springprompt.com/badge/roasbench/google-gemini-4-argon.svg" alt="Gemini 4 Argon is #15 of 36 on ROASBench (Score: 47.0), measured by Spring Prompt" height="20"></a>
Gemini 4 Argon is #54 of 62 on BulletBench (Ladder Elo: 147), measured by Spring Prompt BulletBench · Ladder Elo
<a href="https://springprompt.com/benchmarks/bulletbench?focus=google-gemini-4-argon"><img src="https://springprompt.com/badge/bulletbench/google-gemini-4-argon.svg" alt="Gemini 4 Argon is #54 of 62 on BulletBench (Ladder Elo: 147), measured by Spring Prompt" height="20"></a>

Will Gemini 4 Argon work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.