Model comparison
gpt-oss-120b vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 28× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
MetaSummary
- They share 27 benchmarks with published results for both. gpt-oss-120b scores higher in 0 categories and Muse Spark 1.3 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.3 leads 54.0 to 20.0.
- The biggest single-benchmark swing is APEX-Agents: 4.4% for gpt-oss-120b and 57.8% for Muse Spark 1.3.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Muse Spark 1.3 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 36.3 | 54.8 |
| Released | 2025-08-05 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 41K | 131K |
| Input $ / M tokens | $0.037 | $1.25 |
| Output $ / M tokens | $0.17 | $4.25 |
| Results tracked | 48 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
gpt-oss-120b: 33.5 (#256), Muse Spark 1.3: 56.6 (#21)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| SciCode | 36% | 59.7% |
| LMArena Coding | 1380 | 1514 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Muse Spark 1.3 leads
gpt-oss-120b: 12.2 (#153), Muse Spark 1.3: 38.6 (#30)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | 4.4% | 57.8% |
| Terminal-Bench | 18.7% | — |
| GDP.pdf | — | 27.6% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Muse Spark 1.3 leads
gpt-oss-120b: 20.0 (#245), Muse Spark 1.3: 54.0 (#27)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| CritPt | 1.1% | 26% |
| Chess Puzzles | 20% | 38% |
| LMArena Hard Prompts | 1364 | 1503 |
| Mystery Game Puzzles | 2% | 25% |
| DTBench | 76.3% | 96.5% |
| LMCA | 22.1% | 53.9% |
| Epoch Capabilities Index | 139.93 | 156.75 |
| SimpleBench | 22.1% | — |
| Kagi LLM Benchmark | 58.6% | — |
| NYT Connections (extended) | — | 85.1% |
| Surface Evolver Bench | 25% | — |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
gpt-oss-120b: 52.5 (#50), Muse Spark 1.3: 73.1 (#21)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 99.2% |
| LMArena Math | 1389 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| Omni-MATH | 68.8% | — |
Knowledge Too close to call
gpt-oss-120b: 42.4 (#96), Muse Spark 1.3: 42.6 (#95)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1356 | 1516 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
Multimodal Not comparable
gpt-oss-120b: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
gpt-oss-120b: 48.0 (#147), Muse Spark 1.3: 57.4 (#8)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1351 | 1481 |
| LMArena Chinese | 1385 | 1529 |
| LMArena French | 1369 | 1524 |
| LMArena German | 1353 | 1515 |
| LMArena Japanese | 1331 | 1474 |
| LMArena Korean | 1282 | 1501 |
| LMArena Russian | 1343 | 1490 |
| LMArena Spanish | 1389 | 1490 |
Instruction Following Muse Spark 1.3 leads
gpt-oss-120b: 69.3 (#173), Muse Spark 1.3: 77.5 (#22)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1318 | 1477 |
| IFEval | 83.6% | — |
Long Context Muse Spark 1.3 leads
gpt-oss-120b: 31.4 (#278), Muse Spark 1.3: 45.6 (#32)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1319 | 1488 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Muse Spark 1.3 leads
gpt-oss-120b: 46.5 (#217), Muse Spark 1.3: 73.6 (#9)
| Benchmark | gpt-oss-120b | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1365 | 1490 |
| LMArena Creative Writing | 1275 | 1455 |
| EQ-Bench Creative Writing | 961 | 1906 |
| LMArena Multi-Turn | 1340 | 1482 |
| Short-Story Creative Writing | 77.1% | — |
| WildBench | 84.5% | — |
Frequently asked questions
Is gpt-oss-120b better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 28× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Muse Spark 1.3?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is gpt-oss-120b or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 131K.
How many benchmarks do gpt-oss-120b and Muse Spark 1.3 share?
27 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Muse Spark 1.3 has 37.