Model comparison
gpt-oss-120b vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 to 36.3 on the Noometry Index. gpt-oss-120b costs 43× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. gpt-oss-120b scores higher in 0 categories and Grok 4.6 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 20.0.
- The biggest single-benchmark swing is APEX-Agents: 4.4% for gpt-oss-120b and 65.3% for Grok 4.6.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Grok 4.6 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 36.3 | 56.9 |
| Released | 2025-08-05 | 2026-08-12 |
| Weights | Open | Proprietary |
| Context window | 131K | 500K |
| Max output | 41K | 500K |
| Input $ / M tokens | $0.037 | $2 |
| Output $ / M tokens | $0.17 | $6 |
| Results tracked | 48 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
gpt-oss-120b: 33.5 (#256), Grok 4.6: 58.5 (#16)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| SciCode | 36% | 56.5% |
| WeirdML | 48.2% | 67.3% |
| LMArena Coding | 1380 | 1465 |
| ALE-Bench | 575.62 | 1,508 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Grok 4.6 leads
gpt-oss-120b: 12.2 (#153), Grok 4.6: 39.4 (#27)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| APEX-Agents | 4.4% | 65.3% |
| Vending-Bench 2 | -21.53 | 9,047 |
| Terminal-Bench | 18.7% | — |
| GDP.pdf | — | 17.2% |
| METR Time Horizons | 56.6% | — |
Reasoning Grok 4.6 leads
gpt-oss-120b: 20.0 (#245), Grok 4.6: 61.4 (#20)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| SimpleBench | 22.1% | 75.9% |
| CritPt | 1.1% | 19.7% |
| Chess Puzzles | 20% | 40% |
| LMArena Hard Prompts | 1364 | 1447 |
| Mystery Game Puzzles | 2% | 34% |
| DTBench | 76.3% | 97.3% |
| LMCA | 22.1% | 48.5% |
| Epoch Capabilities Index | 139.93 | 156.44 |
| ARC-AGI-2 | — | 67.1% |
| Kagi LLM Benchmark | 58.6% | — |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| EBR-Bench | — | 30.5% |
| Surface Evolver Bench | 25% | — |
Math Grok 4.6 leads
gpt-oss-120b: 52.5 (#50), Grok 4.6: 67.0 (#24)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 99.2% |
| LMArena Math | 1389 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| ProofBench | — | 51% |
| Omni-MATH | 68.8% | — |
Knowledge Grok 4.6 leads
gpt-oss-120b: 42.4 (#96), Grok 4.6: 63.3 (#20)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| GPQA Diamond | 75.8% | 94% |
| LMArena Expert | 1356 | 1467 |
| SimpleQA Verified | — | 49.3% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multimodal Not comparable
gpt-oss-120b: —, Grok 4.6: 43.6 (#23)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
gpt-oss-120b: 48.0 (#147), Grok 4.6: 53.0 (#74)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1351 | 1420 |
| LMArena Chinese | 1385 | 1480 |
| LMArena French | 1369 | 1461 |
| LMArena German | 1353 | 1431 |
| LMArena Japanese | 1331 | 1376 |
| LMArena Korean | 1282 | 1397 |
| LMArena Russian | 1343 | 1422 |
| LMArena Spanish | 1389 | 1404 |
Instruction Following Grok 4.6 leads
gpt-oss-120b: 69.3 (#173), Grok 4.6: 75.4 (#63)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1431 |
| IFEval | 83.6% | — |
Long Context Grok 4.6 leads
gpt-oss-120b: 31.4 (#278), Grok 4.6: 44.5 (#66)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1319 | 1454 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Grok 4.6 leads
gpt-oss-120b: 46.5 (#217), Grok 4.6: 62.3 (#80)
| Benchmark | gpt-oss-120b | Grok 4.6 |
|---|---|---|
| LMArena Text | 1365 | 1428 |
| LMArena Creative Writing | 1275 | 1428 |
| LMArena Multi-Turn | 1340 | 1425 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 36.3 on the Noometry Index. gpt-oss-120b costs 43× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Grok 4.6?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Grok 4.6 lists at $2 and $6.
Is gpt-oss-120b or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 131K.
How many benchmarks do gpt-oss-120b and Grok 4.6 share?
31 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Grok 4.6 has 49.