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.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe).
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.
At a glance
| 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 | $7.50 (Azure) | $4.38 (Azure) |
| Intelligence Index | 7.3 | 7.7 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 128,000 tokens | 128,000 tokens |
| Released | 13 May 2024 | 6 Aug 2024 (newer) |
| Weights | Closed | Closed |
| Developer based in | the US | the 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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | GPT-4o (2024-05-13) | GPT-4o (2024-08-06) |
|---|---|---|
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 185 of 198 | 179 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 89 of 188 | 152 of 188 |
| Sticking to the factsSummarising without inventing things, and factual answers | not measured | 104 of 152 |
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. 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.
| Measure | GPT-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 | 1,346 | 1,336 |
| Business, management and finance · TextArena rating, higher is better | 1,322 | 1,302 |
| Creative writing · TextArena rating, higher is better | 1,338 | 1,327 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 7.3 | 7.7 |
| GPQA Diamond% of questions, higher is better | 52.6% | 52.1% |
| Humanity's Last Exam% of questions, higher is better | 1.8% | 2.3% |
Show all 9 results (3 more)
| Measure | GPT-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 | 1,311 | 1,311 |
| Instruction following · TextArena rating, higher is better | 1,326 | 1,319 |
| Writing, literature and language · TextArena rating, higher is better | 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.
Run GPT-4o (2024-05-13) and GPT-4o (2024-08-06) on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.