GPT-5.4 vs gpt-oss-120b
Head to head on 18 shared benchmarks, with price, context window, and release dates.
Benchmark scores
52evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.4 OpenAI | 65.3% | 78.0% | 1840elo | 78.3 | 92.0% | 43.7% | 73.9% | 82.0% | 77.5% | 79.3% | 70.2% | 82.6% | 94.1% | 88.1% | 56.6% | 74.0% | 57.6% | 87.1% | - | - | 13.1% | - | - | 1.47 | 34.1% | 9.0% | 1272elo | 47.6% | 87.2% | - | 78.5% | 92063 | - | - | - | 82.8% | 41.3% | 77.5% | - | - | 68.3% | 86 | 52.2% | 56.0% | 43.3% | -0.61 | - | 40.8 | - | - | 80 | 67.4% | 65.4% |
| gpt-oss-120b OpenAI | 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% | 34.0% | 71.6% | 23.5% | 65.8% | 41.8% | 93.4% | - | 38.9% | 7.6% | - | - | - | - | - | - | 57.6 | - | - | 87.8% | 1.62 | 1.53 | - | - | - | 80.0% | 80.8% | - | - | - | - | - | - | 97.9% | - | 26.0% | 65.6% | - | - | 54.1% |
2 / 2 models
| Attribute | GPT-5.4 OpenAI | gpt-oss-120b OpenAI |
|---|---|---|
| Description | GPT-5.4 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 | 5 Mar 2026 | 5 Aug 2025 |
| Context | 1,050,000 | 131,072 |
| Input $/1M | $2.50 | $0.15 |
| Output $/1M | $15.00 | $0.59 |
| Cache read $/1M | $0.250 | $0.075 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 209 tok/s |
| Latency | 0.00 s | 0.51 s |
| Modalities | text, image, file | text |
| Providers | - | - |
| Publisher | OpenAI | OpenAI |
| Reported scores | GPQA Diamond92.0% (AA) SciCode56.6% (AA) τ²-bench (Tau²-bench)87.1% (AA) Terminal-Bench (Hard)57.6% (AA) Vibe Code Bench v1.167.4% | 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-5.4 or gpt-oss-120b better?
- Across the 18 benchmarks both models report on Sophon, GPT-5.4 leads on 18 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do GPT-5.4 and gpt-oss-120b compare on GPQA Diamond?
- GPT-5.4 scores 92.0% and gpt-oss-120b scores 78.2% on GPQA Diamond.
- Which is cheaper, GPT-5.4 or gpt-oss-120b?
- gpt-oss-120b is cheaper at $0.59 per million output tokens against $15.00 for GPT-5.4 - about 25.4x.
- When were GPT-5.4 and gpt-oss-120b released?
- GPT-5.4 was released 5 Mar 2026 by OpenAI. gpt-oss-120b was released 5 Aug 2025 by OpenAI.
Other head-to-heads
56Gemini 3.1 Pro Preview vs GPT-5.434 shared evalsClaude Opus 4.6 vs GPT-5.433 shared evalsGPT-5.2 vs GPT-5.429 shared evalsGPT-5.4 vs GPT-5.528 shared evalsClaude Opus 4.8 vs GPT-5.428 shared evalsClaude Opus 4.5 vs GPT-5.428 shared evalsGPT-5.4 vs Kimi K2.528 shared evalsClaude Sonnet 4.6 vs GPT-5.428 shared evalsClaude Opus 4.7 vs GPT-5.428 shared evalsGPT-5 Mini vs GPT-5.427 shared evalsGPT-5.4 Mini vs GPT-5.427 shared evalsClaude Sonnet 4.5 vs GPT-5.426 shared evalsClaude Fable 5 vs GPT-5.426 shared evalsGLM 5.1 vs GPT-5.426 shared evalsGPT-5 Mini vs gpt-oss-120b25 shared evalsGPT-5.4 vs Grok 4.1 Fast25 shared evalsGPT-5.4 vs Qwen3.6 Plus24 shared evalsDeepSeek V3.2 vs GPT-5.424 shared evalsClaude Sonnet 4.5 vs gpt-oss-120b23 shared evalsDeepSeek V3.2 vs gpt-oss-120b23 shared evalsGPT-5 Nano vs GPT-5.422 shared evalsGPT-5 Nano vs gpt-oss-120b22 shared evalsGPT-5.2 vs gpt-oss-120b22 shared evalsClaude 4 Sonnet vs GPT-5.422 shared evalsClaude Opus 4.5 vs gpt-oss-120b21 shared evalsClaude 4 Sonnet vs gpt-oss-120b21 shared evalsGLM 4.7 vs GPT-5.421 shared evalsGemini 2.5 Pro vs GPT-5.420 shared evalsgpt-oss-120b vs Grok 4.1 Fast20 shared evalsGLM 4.7 vs gpt-oss-120b20 shared evalsGPT-5 vs GPT-5.419 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 evalsClaude Opus 4.8 vs gpt-oss-120b18 shared evalsClaude Fable 5 vs gpt-oss-120b18 shared evalsClaude Sonnet 4.6 vs gpt-oss-120b18 shared evalsClaude Opus 4.7 vs gpt-oss-120b18 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-4o-mini vs gpt-oss-120b15 shared evalsGPT-4o vs GPT-5.414 shared evalsGPT-4.1 Nano vs gpt-oss-120b14 shared evalsGPT-4.1 vs GPT-5.413 shared evalsGPT-5.4 vs GPT-6 Astra13 shared evalsGPT-4.1 Mini vs GPT-5.412 shared evalsGPT-4o-mini vs GPT-5.412 shared evalsGPT-4.1 Nano vs GPT-5.412 shared evalsGPT-6 Astra vs gpt-oss-120b6 shared evals
Comparing something else? Build your own side-by-side.