Model comparison
Gemini 2.5 Pro vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 45.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
MetaSummary
- They share 24 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 3 categories and Muse Spark 1.2 in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 28.8.
- The biggest single-benchmark swing is CritPt: 2% for Gemini 2.5 Pro and 17.7% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
Side by side
| Gemini 2.5 Pro | Muse Spark 1.2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 45.0 | 50.3 |
| Released | 2025-03-25 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $1.25 | $1.25 |
| Output $ / M tokens | $10 | $4.25 |
| Results tracked | 78 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Gemini 2.5 Pro: 42.4 (#101), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1227 | 1533 |
| SciCode | 42.8% | 56.4% |
| WeirdML | 54% | 60.3% |
| LMArena Coding | 1452 | 1495 |
| SWE-bench Verified | 57.6% | — |
| DeepSWE | — | 54.9% |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| FrontierSWE | — | 12% |
| GSO | 3.9% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Too close to call
Gemini 2.5 Pro: 29.2 (#88), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| APEX-Agents | — | 36.4% |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| GDP.pdf | — | 16% |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Muse Spark 1.2 leads
Gemini 2.5 Pro: 28.8 (#99), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 62.4% | 74.5% |
| CritPt | 2% | 17.7% |
| LMArena Hard Prompts | 1455 | 1486 |
| DTBench | 82.4% | 94.7% |
| LMCA | 34.8% | 48.4% |
| Epoch Capabilities Index | 145.32 | 154.87 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 79.2% |
| ARC-AGI-1 | 41% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| LiveBench Data Analysis | 79.9% | — |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |
Math Muse Spark 1.2 leads
Gemini 2.5 Pro: 32.5 (#213), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1450 | 1471 |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| ProofBench | — | 43% |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 56.0 (#46), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1452 | 1480 |
| GPQA Diamond | 85.3% | — |
| Humanity's Last Exam | 21.6% | — |
| SimpleQA Verified | — | 60.3% |
| 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 1.2: 43.4 (#25)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1263 | 1305 |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Muse Spark 1.2 leads
Gemini 2.5 Pro: 55.3 (#31), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1451 | 1478 |
| LMArena Chinese | 1507 | 1511 |
| LMArena French | 1472 | 1513 |
| LMArena Russian | 1461 | 1487 |
| LMArena Spanish | 1473 | 1498 |
| LMArena German | 1487 | — |
| LMArena Japanese | 1461 | — |
| LMArena Korean | 1434 | — |
Instruction Following Muse Spark 1.2 leads
Gemini 2.5 Pro: 75.0 (#75), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1437 | 1461 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1449 | 1475 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Muse Spark 1.2 leads
Gemini 2.5 Pro: 63.7 (#62), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Gemini 2.5 Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1458 | 1482 |
| LMArena Creative Writing | 1454 | 1449 |
| EQ-Bench Creative Writing | 1421 | 1840 |
| LMArena Multi-Turn | 1453 | 1494 |
| Short-Story Creative Writing | 83.8% | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 45.0 on the Noometry Index.
Which is cheaper, Gemini 2.5 Pro or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Is Gemini 2.5 Pro or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 2.5 Pro and Muse Spark 1.2 share?
24 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Muse Spark 1.2 has 31.