GPT-5.2 vs gpt-oss-120b
Head to head on 22 shared benchmarks, with price, context window, and release dates.
Benchmark scores
52evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.2 OpenAI | 99.0% | 65.9% | 56.0% | 1703elo | 71.6 | 90.3% | 37.7% | 75.4% | 78.7% | 76.1% | 78.2% | 61.8% | 79.8% | 93.2% | 83.2% | 88.9% | 87.4% | 52.1% | 71.8% | 75.8% | 47.0% | 84.8% | - | 100 | - | - | 100.0% | 0.0% | 16.7% | 40.6% | 9.4% | 40.7% | 12.93 | - | 85.0% | 79.0% | 24.0% | - | - | 72.0% | 49.7% | 84.4% | - | 67.1% | 96.7 | 18.7% | 15.0% | 49.3% | - | 66.7% | - | 53.5% | 62.0% |
| gpt-oss-120b OpenAI | 93.4% | 58.2% | 11.0% | 961elo | 35.8 | 78.2% | 19.6% | 69.0% | 51.0% | 60.2% | 38.8% | 50.3% | 48.6% | 68.9% | 39.2% | 87.8% | 80.8% | 34.0% | 26.0% | 71.6% | 23.5% | 65.8% | 41.8% | - | 38.9% | 7.6% | - | - | - | - | - | - | - | 57.6 | - | - | - | 1.62 | 1.53 | - | - | - | 80.0% | - | - | - | - | - | 97.9% | - | 65.6% | - | 54.1% |
2 / 2 models
| Attribute | GPT-5.2 OpenAI | gpt-oss-120b OpenAI |
|---|---|---|
| Description | GPT-5.2 is an AI model from OpenAI. | GPT-Oss 120b is an AI model from OpenAI, released with open weights. |
| Family | GPT | GPT |
| Params | - | - |
| Open weights | closed | open |
| License | proprietary | apache-2.0 |
| Released | 11 Dec 2025 | 5 Aug 2025 |
| Context | 400,000 | 131,072 |
| Input $/1M | $1.75 | $0.15 |
| Output $/1M | $14.00 | $0.59 |
| Cache read $/1M | $0.175 | $0.075 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 194 tok/s |
| Latency | 0.00 s | 0.53 s |
| Modalities | file, image, text | text |
| Providers | - | - |
| Publisher | OpenAI | OpenAI |
| Reported scores | GPQA Diamond78.2% (AA) Humanity's Last Exam (HLE)19.6% (AA) LiveCodeBench87.8% (AA) MMLU-Pro80.8% (AA) SciCode34.0% (AA) |
FAQ
- Is GPT-5.2 or gpt-oss-120b better?
- Across the 22 benchmarks both models report on Sophon, GPT-5.2 leads on 22 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-5.2 and gpt-oss-120b compare on GPQA Diamond?
- GPT-5.2 scores 90.3% and gpt-oss-120b scores 78.2% on GPQA Diamond.
- Which is cheaper, GPT-5.2 or gpt-oss-120b?
- gpt-oss-120b is cheaper at $0.59 per million output tokens against $14.00 for GPT-5.2 - about 23.5x.
- When were GPT-5.2 and gpt-oss-120b released?
- GPT-5.2 was released 11 Dec 2025 by OpenAI. gpt-oss-120b was released 5 Aug 2025 by OpenAI.
Other head-to-heads
56Claude Opus 4.5 vs GPT-5.235 shared evalsClaude Sonnet 4.5 vs GPT-5.232 shared evalsGPT-5 Mini vs GPT-5.232 shared evalsClaude Opus 4.6 vs GPT-5.230 shared evalsGPT-5.2 vs Grok 4.1 Fast30 shared evalsGemini 3.1 Pro Preview vs GPT-5.229 shared evalsGPT-5.2 vs GPT-5.429 shared evalsGPT-5.2 vs Kimi K2.529 shared evalsDeepSeek V3.2 vs GPT-5.229 shared evalsGPT-5.2 vs GPT-5.527 shared evalsGPT-5 Nano vs GPT-5.226 shared evalsClaude Opus 4.8 vs GPT-5.226 shared evalsClaude Opus 4.7 vs GPT-5.226 shared evalsGPT-5 Mini vs gpt-oss-120b25 shared evalsClaude 4 Sonnet vs GPT-5.225 shared evalsGLM 5.1 vs GPT-5.225 shared evalsGPT-5.4 Mini vs GPT-5.225 shared evalsClaude Fable 5 vs GPT-5.224 shared evalsClaude Sonnet 4.6 vs GPT-5.224 shared evalsGemini 2.5 Pro vs GPT-5.224 shared evalsGLM 4.7 vs GPT-5.224 shared evalsClaude Sonnet 4.5 vs gpt-oss-120b23 shared evalsGPT-5 vs GPT-5.223 shared evalsGPT-5.2 vs Qwen3.6 Plus23 shared evalsDeepSeek V3.2 vs gpt-oss-120b23 shared evalsGPT-5 Nano vs gpt-oss-120b22 shared evalsClaude Opus 4.5 vs gpt-oss-120b21 shared evalsClaude 4 Sonnet vs gpt-oss-120b21 shared evalsgpt-oss-120b vs Grok 4.1 Fast20 shared evalsGLM 4.7 vs gpt-oss-120b20 shared evalsGPT-5.5 vs gpt-oss-120b19 shared evalsClaude Opus 4.6 vs gpt-oss-120b19 shared evalsgpt-oss-120b vs Kimi K2.519 shared evalsGLM 5.1 vs gpt-oss-120b19 shared evalsGemini 2.5 Pro vs gpt-oss-120b19 shared evalsGemini 3.1 Pro Preview vs gpt-oss-120b18 shared evalsGPT-4o vs GPT-5.218 shared evalsClaude Opus 4.8 vs gpt-oss-120b18 shared evalsClaude Fable 5 vs gpt-oss-120b18 shared evalsGPT-5.4 vs gpt-oss-120b18 shared evalsClaude Sonnet 4.6 vs gpt-oss-120b18 shared evalsClaude Opus 4.7 vs gpt-oss-120b18 shared evalsGPT-4.1 Mini vs GPT-5.217 shared evalsGPT-5 vs gpt-oss-120b17 shared evalsGPT-4o vs gpt-oss-120b17 shared evalsGPT-5.4 Mini vs gpt-oss-120b17 shared evalsGPT-4.1 vs gpt-oss-120b16 shared evalsgpt-oss-120b vs Qwen3.6 Plus16 shared evalsGPT-4.1 Mini vs gpt-oss-120b15 shared evalsGPT-4.1 vs GPT-5.215 shared evalsGPT-4o-mini vs GPT-5.215 shared evalsGPT-4.1 Nano vs GPT-5.215 shared evalsGPT-4o-mini vs gpt-oss-120b15 shared evalsGPT-4.1 Nano vs gpt-oss-120b14 shared evalsGPT-5.2 vs GPT-6 Astra13 shared evalsGPT-6 Astra vs gpt-oss-120b6 shared evals
Comparing something else? Build your own side-by-side.