Model comparison
gpt-oss-20b vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 32.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
MetaSummary
- They share 20 benchmarks with published results for both. gpt-oss-20b scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 34.6.
- The biggest single-benchmark swing is GPQA Diamond: 60.8% for gpt-oss-20b and 89.8% for Muse Spark.
- gpt-oss-20b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-20b | Muse Spark | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 32.5 | 50.6 |
| Released | 2025-08-05 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
gpt-oss-20b: 37.6 (#192), Muse Spark: 46.2 (#69)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| SciCode | 34.4% | 51.5% |
| LMArena Coding | 1306 | 1481 |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Muse Spark: —
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Muse Spark leads
gpt-oss-20b: 19.3 (#261), Muse Spark: 35.9 (#67)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| CritPt | 1.4% | 11.3% |
| LMArena Hard Prompts | 1274 | 1474 |
| Epoch Capabilities Index | 137.82 | 152.04 |
| Kagi LLM Benchmark | 53.2% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
Math Muse Spark leads
gpt-oss-20b: 39.4 (#103), Muse Spark: 47.8 (#66)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 88.9% |
| LMArena Math | 1317 | 1455 |
| ProofBench | — | 17% |
| Omni-MATH | 56.5% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
gpt-oss-20b: 34.6 (#195), Muse Spark: 65.7 (#13)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| GPQA Diamond | 60.8% | 89.8% |
| LMArena Expert | 1258 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multimodal Not comparable
gpt-oss-20b: —, Muse Spark: 43.4 (#24)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
gpt-oss-20b: 42.2 (#197), Muse Spark: 56.1 (#24)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| LMArena Non-English | 1268 | 1464 |
| LMArena Chinese | 1314 | 1509 |
| LMArena German | 1255 | 1497 |
| LMArena Korean | 1236 | 1459 |
| LMArena Russian | 1278 | 1466 |
| LMArena Spanish | 1267 | 1472 |
| LMArena French | — | 1497 |
| LMArena Japanese | 1244 | — |
Instruction Following Muse Spark leads
gpt-oss-20b: 61.8 (#240), Muse Spark: 75.9 (#51)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1236 | 1442 |
| IFEval | 73.2% | — |
Long Context Muse Spark leads
gpt-oss-20b: 37.9 (#209), Muse Spark: 44.4 (#69)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1250 | 1451 |
Writing & Preference Muse Spark leads
gpt-oss-20b: 35.5 (#265), Muse Spark: 66.0 (#39)
| Benchmark | gpt-oss-20b | Muse Spark |
|---|---|---|
| LMArena Text | 1287 | 1474 |
| LMArena Creative Writing | 1201 | 1459 |
| LMArena Multi-Turn | 1268 | 1477 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 32.5 on the Noometry Index.
Is gpt-oss-20b or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 37.6 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Muse Spark share?
20 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Muse Spark has 27.