Model comparison
Gemini 2.5 Pro vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 45.0 on the Noometry Index.
Last verified . 26 shared benchmarks.
Google
MetaSummary
- They share 26 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 2 categories and Muse Spark in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 44.4.
- The biggest single-benchmark swing is Humanity's Last Exam: 21.6% for Gemini 2.5 Pro and 40.6% for Muse Spark.
Side by side
| Gemini 2.5 Pro | Muse Spark | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 45.0 | 50.6 |
| Released | 2025-03-25 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 78 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Gemini 2.5 Pro: 42.4 (#101), Muse Spark: 46.2 (#69)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| SciCode | 42.8% | 51.5% |
| LMArena Coding | 1452 | 1481 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| LMArena WebDev | 1227 | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Pro: 29.2 (#88), Muse Spark: —
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Muse Spark leads
Gemini 2.5 Pro: 28.8 (#99), Muse Spark: 35.9 (#67)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| CritPt | 2% | 11.3% |
| LMArena Hard Prompts | 1455 | 1474 |
| Epoch Capabilities Index | 145.32 | 152.04 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 41% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| DTBench | 82.4% | — |
| LiveBench Data Analysis | 79.9% | — |
| LMCA | 34.8% | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |
Math Muse Spark leads
Gemini 2.5 Pro: 32.5 (#213), Muse Spark: 47.8 (#66)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.7% | 88.9% |
| LMArena Math | 1450 | 1455 |
| FrontierMath (Feb 2025 set) | 14.1% | 39% |
| FrontierMath Tier 4 (v1) | 4.2% | 14.6% |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| ProofBench | — | 17% |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |
Knowledge Muse Spark leads
Gemini 2.5 Pro: 56.0 (#46), Muse Spark: 65.7 (#13)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| GPQA Diamond | 85.3% | 89.8% |
| Humanity's Last Exam | 21.6% | 40.6% |
| LMArena Expert | 1452 | 1457 |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |
Multimodal Gemini 2.5 Pro leads
Gemini 2.5 Pro: 45.2 (#18), Muse Spark: 43.4 (#24)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| LMArena Vision | 1263 | 1306 |
| LMArena Document | 1421 | 1444 |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Too close to call
Gemini 2.5 Pro: 55.3 (#31), Muse Spark: 56.1 (#24)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| LMArena Non-English | 1451 | 1464 |
| LMArena Chinese | 1507 | 1509 |
| LMArena French | 1472 | 1497 |
| LMArena German | 1487 | 1497 |
| LMArena Korean | 1434 | 1459 |
| LMArena Russian | 1461 | 1466 |
| LMArena Spanish | 1473 | 1472 |
| LMArena Japanese | 1461 | — |
Instruction Following Too close to call
Gemini 2.5 Pro: 75.0 (#75), Muse Spark: 75.9 (#51)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1437 | 1442 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), Muse Spark: 44.4 (#69)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1449 | 1451 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Muse Spark leads
Gemini 2.5 Pro: 63.7 (#62), Muse Spark: 66.0 (#39)
| Benchmark | Gemini 2.5 Pro | Muse Spark |
|---|---|---|
| LMArena Text | 1458 | 1474 |
| LMArena Creative Writing | 1454 | 1459 |
| LMArena Multi-Turn | 1453 | 1477 |
| Short-Story Creative Writing | 83.8% | — |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 45.0 on the Noometry Index.
Is Gemini 2.5 Pro or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 42.4 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Pro and Muse Spark share?
26 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Muse Spark has 27.