Up to four models
Gemini 3.8 Flash vs Muse Spark 1.3
On the index (GPT-4 = 100), Gemini 3.8 Flash scores 173 and Muse Spark 1.3 169. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
173157–189
WeightsClosed
ReleasedSep 2026
Price in / out$0.82 / $4.13
Context1.05M
Core tests taken7 of 9
169153–186
WeightsClosed
ReleasedSep 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken4 of 9
Gemini 3.8 Flash and Muse Spark 1.3 are too close to call (3 points apart, within the uncertainty), ahead on 3 of 4 shared core tests, at a similar price.
Test by testthird-party results
Every result as a table
| Test | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| Reasoning & knowledge | ||
| GeoBench | 86.0% | 86.0% |
| SimpleBench | 82.4% | 81.8% |
| Maths | ||
| FrontierMath (tiers 1-3) | 68.4% | 74.4% |
| AIME-style maths (OTIS mock) | 98.9% | 99.2% |
| ProofBench v1.1 | 48.0% | 55.0% |
| Chess puzzles | 58.0% | 37.0% |
| FrontierMath (tier 4) | 21.9% | 46.3% |
| Coding | ||
| Terminal-Bench 4.0 | 19.7% | 10.6% |
| Code Migration | 36.5% | 27.6% |
| CyberBench v1.1 | 43.8% | 69.4% |
| IOI | 56.9% | 43.9% |
| ProgramBench | 1.0% | 0.5% |
| Vibe Code Bench v1.1 | 78.6% | 82.9% |
| FrontierSWE | 19.6% | 25.8% |
| MirrorCode | 38.9% | 54.4% |
| Agents | ||
| APEX-Agents | 64.3% | 58.6% |
| Terminal-Bench-Science | 8.6% | 4.3% |
| DTBench | 95.7% | 96.5% |
| LMCA | 52.9% | 53.9% |
| Mystery game puzzles | 47.0% | 25.0% |
| Professional work | ||
| Finance Agent (v2) | 61.4% | 58.9% |
| EMB | 72.2% | 62.7% |
| Legal Research Bench | 38.9% | 40.9% |
| Tax Agent Bench | 32.1% | 37.9% |
Tests at least two of these models have taken. Bold rows are the core tests.