Model comparison
gpt-oss-120b vs Grok 3
Grok 3 is the stronger model overall, scoring 39.9 to 36.3 on the Noometry Index.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Grok 3 in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Grok 3 leads 30.5 to 12.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 55.6% for Grok 3.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Grok 3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 36.3 | 39.9 |
| Released | 2025-08-05 | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 41K | — |
| Input $ / M tokens | $0.037 | — |
| Output $ / M tokens | $0.17 | — |
| Results tracked | 48 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
gpt-oss-120b: 33.5 (#256), Grok 3: 41.9 (#115)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| Aider Polyglot | 41.8% | 53.3% |
| WeirdML | 48.2% | 37.2% |
| LMArena Coding | 1380 | 1432 |
| SWE-bench Verified (bash only) | 26% | — |
| SciCode | 36% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Grok 3 leads
gpt-oss-120b: 12.2 (#153), Grok 3: 30.5 (#76)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| BALROG | — | 29.5% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 20.0 (#245), Grok 3: 13.7 (#333)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| SimpleBench | 22.1% | 36.1% |
| Kagi LLM Benchmark | 58.6% | 61.3% |
| LMArena Hard Prompts | 1364 | 1434 |
| Epoch Capabilities Index | 139.93 | 138.33 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 5.5% |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Grok 3: 38.0 (#145)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 55.6% |
| Omni-MATH | 68.8% | 46.4% |
| LMArena Math | 1389 | 1391 |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Grok 3 leads
gpt-oss-120b: 42.4 (#96), Grok 3: 46.2 (#82)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| GPQA Diamond | 75.8% | 75.8% |
| MMLU-Pro | 79.5% | 78.8% |
| Confabulations | 15.7% | 14.2% |
| Vectara Hallucination Rate | 14.2% | 5.8% |
| GPQA (HELM) | 68.4% | 65% |
| LMArena Expert | 1356 | 1421 |
Multilingual Grok 3 leads
gpt-oss-120b: 48.0 (#147), Grok 3: 52.3 (#87)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| LMArena Non-English | 1351 | 1410 |
| LMArena Chinese | 1385 | 1448 |
| LMArena French | 1369 | 1460 |
| LMArena German | 1353 | 1431 |
| LMArena Japanese | 1331 | 1387 |
| LMArena Korean | 1282 | 1373 |
| LMArena Russian | 1343 | 1416 |
| LMArena Spanish | 1389 | 1417 |
Instruction Following Grok 3 leads
gpt-oss-120b: 69.3 (#173), Grok 3: 75.0 (#73)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| IFEval | 83.6% | 88.4% |
| LMArena Instruction Following | 1318 | 1409 |
Long Context Grok 3 leads
gpt-oss-120b: 31.4 (#278), Grok 3: 38.7 (#192)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| Fiction.LiveBench | 44.4% | 58.3% |
| LMArena Longer Query | 1319 | 1439 |
Writing & Preference Grok 3 leads
gpt-oss-120b: 46.5 (#217), Grok 3: 55.8 (#141)
| Benchmark | gpt-oss-120b | Grok 3 |
|---|---|---|
| LMArena Text | 1365 | 1426 |
| LMArena Creative Writing | 1275 | 1414 |
| Short-Story Creative Writing | 77.1% | 76.4% |
| EQ-Bench Creative Writing | 961 | 1186 |
| WildBench | 84.5% | 84.9% |
| LMArena Multi-Turn | 1340 | 1425 |
Frequently asked questions
Is gpt-oss-120b better than Grok 3?
Grok 3 is the stronger model overall, scoring 39.9 to 36.3 on the Noometry Index.
Is gpt-oss-120b or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.9 versus 33.5 in the Noometry coding category.
How many benchmarks do gpt-oss-120b and Grok 3 share?
34 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Grok 3 has 40.