Compare / GPT-4o (2024-05-13) vs GPT-4o (2024-08-06)

GPT-4o (2024-05-13) vs GPT-4o (2024-08-06)

Which is cheaper, which is more capable, and which does better at each kind of work, from 9 results on 2 sources that measured both models.

OpenAIGPT-4o (2024-05-13) Released 13 May 2024 · $5.00 in · $15.00 out
OpenAIGPT-4o (2024-08-06) Released 6 Aug 2024 · $2.50 in · $10.00 out
GPT-4o (2024-05-13) wins 34 too close to callGPT-4o (2024-08-06) wins 2

Of the 9 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

GPT-4o (2024-05-13) or GPT-4o (2024-08-06)? The short answer

GPT-4o (2024-08-06) is the newer version; they score about the same, so pick GPT-4o (2024-08-06), which costs less (42% less per token).

  • GPT-4o (2024-08-06) is cheaper: $4.38 against $7.50 per million tokens, 42% less.
  • They score about the same on the Artificial Analysis Intelligence Index (7.3 and 7.7).
  • GPT-4o (2024-08-06) is newer: released 6 Aug 2024, against 13 May 2024 for GPT-4o (2024-05-13).
  • On third-party benchmarks, on the results both models have: GPT-4o (2024-05-13) does better for writing; GPT-4o (2024-08-06) for reasoning and knowledge.

Head to head

7.3
Intelligence Index
7.7
$7.50
Price per million tokens, blendedlower is better
$4.38
128,000
Context window, tokens
128,000

Every fact side by side

GPT-4o (2024-05-13)GPT-4o (2024-08-06)
Price per million tokens$5.00 in · $15.00 out$2.50 in · $10.00 out
Blended (3 in : 1 out)$7.50$4.38
Cheapest host, blended–$4.38 (Azure)
Intelligence Index7.37.7
Spring Prompt overall––
Output speed, tokens a second––
Context window128,000 tokens128,000 tokens
Released13 May 20246 Aug 2024 (newer)
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Reasoning and knowledgeHard questions across science, maths and general knowledge 171 of 187 168 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 86 of 169 134 of 169
Sticking to the factsSummarising without inventing things, and factual answers not measured 96 of 139

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureGPT-4o (2024-05-13)GPT-4o (2024-08-06)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 196 · 212 of 387 measured 1,346 1,336
Business, management and finance · TextArena rating, higher is better 214 · 241 of 380 measured 1,322 1,302
Creative writing · TextArena rating, higher is better 166 · 178 of 385 measured 1,338 1,327
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 213 · 205 of 249 measured 7.3 7.7
GPQA Diamond% of questions, higher is better 197 · 198 of 232 measured 52.6% 52.1%
Humanity's Last Exam% of questions, higher is better 250 · 249 of 250 measured 1.8% 2.3%
Show all 9 results (3 more)
MeasureGPT-4o (2024-05-13)GPT-4o (2024-08-06)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 226 · 225 of 338 measured 1,311 1,311
Instruction following · TextArena rating, higher is better 202 · 209 of 387 measured 1,326 1,319
Writing, literature and language · TextArena rating, higher is better 171 · 179 of 386 measured 1,345 1,341

Quick answers

Is GPT-4o (2024-05-13) better than GPT-4o (2024-08-06)?

GPT-4o (2024-08-06) is the newer version; they score about the same, so pick GPT-4o (2024-08-06), which costs less (42% less per token).

Which is cheaper, GPT-4o (2024-05-13) or GPT-4o (2024-08-06)?

GPT-4o (2024-08-06) is cheaper: $4.38 against $7.50 per million tokens, 42% less.

Which is better for reasoning and knowledge, GPT-4o (2024-05-13) or GPT-4o (2024-08-06)?

GPT-4o (2024-08-06) ranks 168 of 187 models on sale for hard questions across science, maths and general knowledge, against 171 for GPT-4o (2024-05-13).

Which is better for writing, GPT-4o (2024-05-13) or GPT-4o (2024-08-06)?

GPT-4o (2024-05-13) ranks 86 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 134 for GPT-4o (2024-08-06).

Run GPT-4o (2024-05-13) and GPT-4o (2024-08-06) on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.