Model comparison
gpt-oss-20b vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 32.5 on the Noometry Index. gpt-oss-20b costs 43× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 19.3.
- The biggest single-benchmark swing is Terminal-Bench: 3.4% for gpt-oss-20b and 57.3% for Grok 4.20 (Non-Reasoning).
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 131K.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 32.5 | 48.6 |
| Released | 2025-08-05 | 2026-02-17 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 30K |
| Input $ / M tokens | $0.018 | $1.25 |
| Output $ / M tokens | $0.09 | $2.50 |
| Results tracked | 34 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 37.6 (#192), Grok 4.20 (Non-Reasoning): 42.1 (#112)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 40.9% | 52.3% |
| LMArena Coding | 1306 | 1459 |
| ALE-Bench | 566.05 | 1,150 |
| LMArena WebDev | — | 1375 |
| SciCode | 34.4% | — |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 9.3 (#154), Grok 4.20 (Non-Reasoning): 34.4 (#46)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | 3.4% | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 19.3 (#261), Grok 4.20 (Non-Reasoning): 52.3 (#32)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 75% |
| Chess Puzzles | 4% | 24% |
| LMArena Hard Prompts | 1274 | 1451 |
| DTBench | 68% | 90.1% |
| LMCA | 14.5% | 38.7% |
| Epoch Capabilities Index | 137.82 | 151.98 |
| ARC-AGI-2 | — | 65.1% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| CritPt | 1.4% | — |
| Thematic Generalization | — | 63.8% |
| ForecastBench | — | 61.4 |
Math Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 39.4 (#103), Grok 4.20 (Non-Reasoning): 48.2 (#65)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 92.2% |
| LMArena Math | 1317 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| Omni-MATH | 56.5% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 34.6 (#195), Grok 4.20 (Non-Reasoning): 52.8 (#60)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 60.8% | 89.3% |
| LMArena Expert | 1258 | 1439 |
| SimpleQA Verified | — | 30.2% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
gpt-oss-20b: —, Grok 4.20 (Non-Reasoning): 33.3 (#98)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 42.2 (#197), Grok 4.20 (Non-Reasoning): 54.5 (#40)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1268 | 1441 |
| LMArena Chinese | 1314 | 1481 |
| LMArena German | 1255 | 1465 |
| LMArena Japanese | 1244 | 1449 |
| LMArena Korean | 1236 | 1417 |
| LMArena Russian | 1278 | 1458 |
| LMArena Spanish | 1267 | 1443 |
| LMArena French | — | 1476 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 61.8 (#240), Grok 4.20 (Non-Reasoning): 74.8 (#83)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1236 | 1420 |
| IFEval | 73.2% | — |
Long Context Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 37.9 (#209), Grok 4.20 (Non-Reasoning): 45.5 (#34)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1250 | 1437 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
gpt-oss-20b: 35.5 (#265), Grok 4.20 (Non-Reasoning): 65.7 (#44)
| Benchmark | gpt-oss-20b | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1287 | 1451 |
| LMArena Creative Writing | 1201 | 1438 |
| EQ-Bench Creative Writing | 666 | 1574 |
| LMArena Multi-Turn | 1268 | 1456 |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 32.5 on the Noometry Index. gpt-oss-20b costs 43× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Grok 4.20 (Non-Reasoning)?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is gpt-oss-20b or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 131K.
How many benchmarks do gpt-oss-20b and Grok 4.20 (Non-Reasoning) share?
27 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.