Leaderboard · Model · Updated
GPT-4o
OpenAI's omnimodal model — strong general-purpose chat with vision and audio.
At a glance
| Provider | OpenAI |
|---|---|
| Released | 2024-05 |
| Tier | general-purpose |
| License | Closed / proprietary |
| Modalities | text, image, audio |
| Context window | 128k tokens |
| Max output | 16.384k tokens |
| API price · input | $2.50 / 1M tokens |
| API price · output | $10.00 / 1M tokens |
Benchmark performance
How GPT-4o stacks up against the current leader (GPT-5) and the median model in the leaderboard:
| Benchmark | GPT-4o | GPT-5 | Median |
|---|---|---|---|
| Chatbot Arena Elo | 1380 | 1410 | 1320 |
| MMLU-Pro | 74.7 | 86.8 | 78.0 |
| GPQA Diamond | 53.6 | 87.3 | 65.0 |
| MATH | 76.6 | 96.7 | 78.3 |
| HumanEval | 90.2 | 95.1 | 92.0 |
| SWE-Bench Verified | 38.8 | 74.9 | 49.0 |
Numbers compiled from provider technical reports and Chatbot Arena. See methodology for the composite-score formula.
OpenRouter routes your requests across GPT-4o, GPT-5, Claude, Gemini, and 100+ other models behind a single API key — pay-as-you-go, no monthly minimum. Try OpenRouter → (affiliate · supports this site)
What does GPT-4o cost in practice?
API pricing is $2.50 per 1M input tokens and $10.00 per 1M output tokens. Assuming a 50/50 input/output split, here is what that looks like at three workload sizes:
| Volume | Per day | Per month | Per year |
|---|---|---|---|
| 1M tokens/day | $6.25 | $187.50 | $2,281 |
| 10M tokens/day | $62.50 | $1,875 | $22,813 |
| 100M tokens/day | $625.00 | $18,750 | $228,125 |
Strengths & weaknesses
Where it shines
- Arena: 1380 (rank #7 of 27, above average)
Where it lags
- SWE-Bench: 38.8 (rank #17 of 18, below average)
- MATH: 76.6 (rank #22 of 29, mid-pack)
- GPQA: 53.6 (rank #20 of 29, mid-pack)
Best alternatives
The closest models to GPT-4o by tier and benchmark score:
| Model | Score | $ in / out | Context | Action |
|---|---|---|---|---|
| Gemini 1.5 Pro |
67.9 | $1.25 / $5.00 | 2M | Try → · vs GPT-4o |
| Claude 3.5 Sonnet Anthropic |
69.1 | $3.00 / $15.00 | 200k | Try → · vs GPT-4o |
| Mistral Large 2 Mistral AI |
63.7 | $2.00 / $6.00 | 128k | Try → · vs GPT-4o |
| GPT-4.1 OpenAI |
74.5 | $2.00 / $8.00 | 1M | Try → · vs GPT-4o |
| Claude 3.7 Sonnet Anthropic |
76.0 | $3.00 / $15.00 | 200k | Try → · vs GPT-4o |
Frequently asked questions
Is GPT-4o a good model?
GPT-4o scores 66.8 on the llmrank.top composite (rank #20 of 30). It trails the frontier — for top performance, look at GPT-5 (86.0). Whether it's the right fit depends on your workload — see the use-case discussion on this page.
How much does GPT-4o cost?
GPT-4o is priced at $2.50 per 1M input tokens and $10.00 per 1M output tokens (USD). For a 10M-token-per-day workload split 50/50, that works out to roughly $62.50/day or $22,813/year.
What is GPT-4o's context window?
128k tokens. For very long inputs, consider a 1M+ context model like Gemini 2.5 Pro or GPT-4.1.
Is GPT-4o open source?
No — it is a closed (proprietary) model accessed only via the provider API.
What is GPT-4o's SWE-Bench score?
GPT-4o scores 38.8% on SWE-Bench Verified — the benchmark that measures real-world GitHub issue resolution. Its Chatbot Arena Elo is 1380.
What are the best alternatives to GPT-4o?
Closest alternatives by tier and score: Gemini 1.5 Pro, Claude 3.5 Sonnet, Mistral Large 2. See the alternatives section on this page for side-by-side numbers.
Related: Gemini 1.5 Pro · Claude 3.5 Sonnet · Mistral Large 2 · Full leaderboard
Spotted out-of-date numbers? Open an issue — corrections usually ship within 24h.
Try GPT-4o now
Direct link to the official playground — or use OpenRouter to A/B test it against any other model on a single API key.