gpt-oss-120b vs Grok 4.5
gpt-oss-120b (OpenAI) and Grok 4.5 (xAI) compared on benchmarks, pricing, context window, and use-case rankings.
- Grok 4.5 leads on overall intelligence (ECI 154 vs 141).
- gpt-oss-120b is cheaper on input tokens — $0.04 vs $2.00 per 1M.
- Grok 4.5 has a larger context window (500K vs 131K tokens).
- Grok 4.5 ranks higher for coding (91th vs 43th percentile).
| Attribute | gpt-oss-120b | Grok 4.5 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 141 | 154 |
| Coding | 43 | 91 |
| Math | 48 | 85 |
| Reasoning & Knowledge | 21 | 70 |
| Agentic & Tools | 10 | 75 |
| Specifications | ||
| Developer | OpenAI | xAI |
| Family | GPT | Grok |
| Released | Aug 5, 2025 | Jul 8, 2026 |
| Parameters | 116.8B | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | 131K | 500K |
| Price — $/M input | $0.04 | $2.00 |
| Price — $/M output | $0.17 | $6.00 |
| Inputs | text | text, image, file |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 89% | 98% |
| APEX | 5% | 34% |
| GPQA Diamond | 76% | 93% |
| Humanity's Last Exam | 19% | 40% |
| LiveCodeBench | 88% | — |
| METR task horizon | 42 min | — |
| MMLU-Pro | 81% | — |
| SciCode | 39% | 54% |
| SimpleBench | 22% | 70% |
| SimpleQA Verified | 14% | 54% |
| Terminal-Bench | 19% | — |
| WeirdML | 48% | 46% |
| τ²-bench | 66% | — |
| ARC-AGI | — | 87% |
| ARC-AGI-2 | — | 53% |
| WebDev Arena | — | 1551 |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is gpt-oss-120b better than Grok 4.5?
On Epoch AI's Capabilities Index, Grok 4.5 scores higher (154) than gpt-oss-120b (141). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, gpt-oss-120b or Grok 4.5?
gpt-oss-120b is cheaper on input tokens at $0.04 per million, versus $2.00 (representative OpenRouter pricing).
Which has a larger context window, gpt-oss-120b or Grok 4.5?
Grok 4.5 supports up to 500K tokens, compared with 131K for the other.
Which is better for coding, gpt-oss-120b or Grok 4.5?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Grok 4.5 ranks higher — 91th vs 43th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.