Model comparison
gpt-oss-20b vs Grok 4 Fast
Grok 4 Fast is the stronger model overall, scoring 39.4 to 32.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. gpt-oss-20b scores higher in 3 categories and Grok 4 Fast in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 Fast leads 63.2 to 37.9.
- The biggest single-benchmark swing is DTBench: 68% for gpt-oss-20b and 82.7% for Grok 4 Fast.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Grok 4 Fast | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 32.5 | 39.4 |
| Released | 2025-08-05 | 2025-09-19 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.6 (#192), Grok 4 Fast: 32.5 (#271)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| WeirdML | 40.9% | 42.9% |
| LMArena Coding | 1306 | 1429 |
| LMArena WebDev | — | 1159 |
| SciCode | 34.4% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Grok 4 Fast leads
gpt-oss-20b: 9.3 (#154), Grok 4 Fast: 29.5 (#86)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| τ²-bench Banking | — | 15.7% |
| Cybench | — | 30% |
| LMArena Search | — | 1171 |
Reasoning Grok 4 Fast leads
gpt-oss-20b: 19.3 (#261), Grok 4 Fast: 22.2 (#201)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 66.1% |
| LMArena Hard Prompts | 1274 | 1412 |
| DTBench | 68% | 82.7% |
| Epoch Capabilities Index | 137.82 | 144.2 |
| ARC-AGI-2 | — | 5.3% |
| ARC-AGI-1 | — | 48.5% |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| LMCA | 14.5% | — |
| ForecastBench | — | 60.5 |
Math Too close to call
gpt-oss-20b: 39.4 (#103), Grok 4 Fast: 38.9 (#123)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1317 | 1419 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), Grok 4 Fast: 32.0 (#214)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| LMArena Expert | 1258 | 1411 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| Vectara Hallucination Rate | — | 19.7% |
| GPQA (HELM) | 59.4% | — |
Multilingual Grok 4 Fast leads
gpt-oss-20b: 42.2 (#197), Grok 4 Fast: 51.3 (#111)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1268 | 1396 |
| LMArena Chinese | 1314 | 1457 |
| LMArena German | 1255 | 1383 |
| LMArena Japanese | 1244 | 1352 |
| LMArena Korean | 1236 | 1357 |
| LMArena Russian | 1278 | 1389 |
| LMArena Spanish | 1267 | 1415 |
| LMArena French | — | 1431 |
Instruction Following Grok 4 Fast leads
gpt-oss-20b: 61.8 (#240), Grok 4 Fast: 73.2 (#121)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1236 | 1387 |
| IFEval | 73.2% | — |
Long Context Grok 4 Fast leads
gpt-oss-20b: 37.9 (#209), Grok 4 Fast: 63.2 (#3)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| LMArena Longer Query | 1250 | 1415 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Grok 4 Fast leads
gpt-oss-20b: 35.5 (#265), Grok 4 Fast: 60.0 (#102)
| Benchmark | gpt-oss-20b | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1287 | 1407 |
| LMArena Creative Writing | 1201 | 1387 |
| LMArena Multi-Turn | 1268 | 1414 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Grok 4 Fast?
Grok 4 Fast is the stronger model overall, scoring 39.4 to 32.5 on the Noometry Index.
Is gpt-oss-20b or Grok 4 Fast better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 32.5 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Grok 4 Fast share?
20 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Grok 4 Fast has 30.