Model comparison
gpt-oss-120b vs Grok-2 (Dec 2024)
gpt-oss-120b is the stronger model overall, scoring 36.3 to 33.7 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. gpt-oss-120b scores higher in 6 categories and Grok-2 (Dec 2024) in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 11.5% for Grok-2 (Dec 2024).
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 36.3 | 33.7 |
| Released | 2025-08-05 | 2024-08-13 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 41K | — |
| Input $ / M tokens | $0.037 | — |
| Output $ / M tokens | $0.17 | — |
| Results tracked | 48 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
gpt-oss-120b: 33.5 (#256), Grok-2 (Dec 2024): 33.3 (#258)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 48.2% | 22.2% |
| LMArena Coding | 1380 | 1287 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.2 (#153), Grok-2 (Dec 2024): —
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Grok-2 (Dec 2024): 16.9 (#299)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 22.1% | 22.7% |
| LMArena Hard Prompts | 1364 | 1272 |
| DTBench | 76.3% | 65.2% |
| Epoch Capabilities Index | 139.93 | 130.48 |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| LiveBench Reasoning | — | 54.8% |
| Mystery Game Puzzles | 2% | — |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| LiveBench | — | 54.3% |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Grok-2 (Dec 2024): 20.8 (#284)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 11.5% |
| LMArena Math | 1389 | 1283 |
| Omni-MATH | 68.8% | — |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.4 (#96), Grok-2 (Dec 2024): 29.8 (#233)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 75.8% | 53.8% |
| Confabulations | 15.7% | 20.1% |
| LMArena Expert | 1356 | 1254 |
| MMLU-Pro | 79.5% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multilingual gpt-oss-120b leads
gpt-oss-120b: 48.0 (#147), Grok-2 (Dec 2024): 43.1 (#188)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1351 | 1282 |
| LMArena Chinese | 1385 | 1289 |
| LMArena French | 1369 | 1318 |
| LMArena German | 1353 | 1287 |
| LMArena Japanese | 1331 | 1244 |
| LMArena Korean | 1282 | 1237 |
| LMArena Russian | 1343 | 1286 |
| LMArena Spanish | 1389 | 1281 |
Instruction Following gpt-oss-120b leads
gpt-oss-120b: 69.3 (#173), Grok-2 (Dec 2024): 66.9 (#202)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1318 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
| IFEval | 83.6% | — |
Long Context Grok-2 (Dec 2024) leads
gpt-oss-120b: 31.4 (#278), Grok-2 (Dec 2024): 38.8 (#190)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1319 | 1276 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Grok-2 (Dec 2024) leads
gpt-oss-120b: 46.5 (#217), Grok-2 (Dec 2024): 48.6 (#198)
| Benchmark | gpt-oss-120b | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1365 | 1305 |
| LMArena Creative Writing | 1275 | 1284 |
| Short-Story Creative Writing | 77.1% | 63.6% |
| LMArena Multi-Turn | 1340 | 1290 |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is gpt-oss-120b better than Grok-2 (Dec 2024)?
gpt-oss-120b is the stronger model overall, scoring 36.3 to 33.7 on the Noometry Index.
Is gpt-oss-120b or Grok-2 (Dec 2024) better for coding?
They score almost the same on coding (33.5 vs 33.3); test both on your own repository before choosing.
How many benchmarks do gpt-oss-120b and Grok-2 (Dec 2024) share?
25 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Grok-2 (Dec 2024) has 34.