Model comparison
gpt-oss-20b vs Grok 4.3
Grok 4.3 is the stronger model overall, scoring 43.8 to 32.5 on the Noometry Index. gpt-oss-20b costs 43× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Grok 4.3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.3 leads 58.5 to 35.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 93.3% for Grok 4.3.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
- Grok 4.3 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 4.3 | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 32.5 | 43.8 |
| Released | 2025-08-05 | 2026-04-17 |
| 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 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.3 leads
gpt-oss-20b: 37.6 (#192), Grok 4.3: 41.6 (#121)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| SciCode | 34.4% | 47.3% |
| WeirdML | 40.9% | 49.9% |
| LMArena Coding | 1306 | 1415 |
| ALE-Bench | 566.05 | 944.17 |
| LMArena WebDev | — | 1357 |
Agentic & Tool Use Grok 4.3 leads
gpt-oss-20b: 9.3 (#154), Grok 4.3: 27.7 (#99)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| GDP.pdf | — | 8% |
| LMArena Search | — | 1165 |
| Vending-Bench 2 | — | 35.26 |
Reasoning Grok 4.3 leads
gpt-oss-20b: 19.3 (#261), Grok 4.3: 35.9 (#68)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| CritPt | 1.4% | 8% |
| Chess Puzzles | 4% | 25% |
| LMArena Hard Prompts | 1274 | 1396 |
| DTBench | 68% | 90.7% |
| LMCA | 14.5% | 38.3% |
| Epoch Capabilities Index | 137.82 | 149.16 |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 55.2% |
| ForecastBench | — | 60.3 |
Math Grok 4.3 leads
gpt-oss-20b: 39.4 (#103), Grok 4.3: 46.0 (#74)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 93.3% |
| LMArena Math | 1317 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| ProofBench | — | 11% |
| Omni-MATH | 56.5% | — |
Knowledge Grok 4.3 leads
gpt-oss-20b: 34.6 (#195), Grok 4.3: 52.5 (#62)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| GPQA Diamond | 60.8% | 88.8% |
| LMArena Expert | 1258 | 1385 |
| SimpleQA Verified | — | 33.2% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
gpt-oss-20b: —, Grok 4.3: 31.6 (#104)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| LMArena Vision | — | 1229 |
| Blueprint-Bench 2 | — | 0% |
Multilingual Grok 4.3 leads
gpt-oss-20b: 42.2 (#197), Grok 4.3: 50.5 (#120)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1268 | 1385 |
| LMArena Chinese | 1314 | 1422 |
| LMArena German | 1255 | 1395 |
| LMArena Japanese | 1244 | 1379 |
| LMArena Korean | 1236 | 1356 |
| LMArena Russian | 1278 | 1399 |
| LMArena Spanish | 1267 | 1398 |
| LMArena French | — | 1412 |
Instruction Following Grok 4.3 leads
gpt-oss-20b: 61.8 (#240), Grok 4.3: 72.1 (#140)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1236 | 1366 |
| IFEval | 73.2% | — |
Long Context Grok 4.3 leads
gpt-oss-20b: 37.9 (#209), Grok 4.3: 42.5 (#123)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1250 | 1393 |
Writing & Preference Grok 4.3 leads
gpt-oss-20b: 35.5 (#265), Grok 4.3: 58.5 (#118)
| Benchmark | gpt-oss-20b | Grok 4.3 |
|---|---|---|
| LMArena Text | 1287 | 1397 |
| LMArena Creative Writing | 1201 | 1380 |
| LMArena Multi-Turn | 1268 | 1406 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| EQ-Bench 4 | — | 1075 |
Frequently asked questions
Is gpt-oss-20b better than Grok 4.3?
Grok 4.3 is the stronger model overall, scoring 43.8 to 32.5 on the Noometry Index. gpt-oss-20b costs 43× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-20b or Grok 4.3?
gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.
Is gpt-oss-20b or Grok 4.3 better for coding?
Grok 4.3 scores higher on coding benchmarks: 41.6 versus 37.6 in the Noometry coding category.
Which has the bigger context window?
Grok 4.3 does, with 1M tokens against 131K.
How many benchmarks do gpt-oss-20b and Grok 4.3 share?
26 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Grok 4.3 has 40.