Muse Glimmer-30BvsGemma 4 31B
Across 3 shared benchmarks, Gemma 4 31B leads overall: Muse Glimmer-30B wins 1, Gemma 4 31B wins 2, with 0 ties and an average score difference of +0.07.
Muse Glimmer-30B
Facebook AI研究实验室 · 2026-08-10 · Reasoning model
Gemma 4 31B
DeepMind · 2026-04-02 · Chat model
Muse Glimmer-30B1 win(33%)(67%)2 winsGemma 4 31B
Benchmark scores
Grouped by capability, sorted by largest gap within each. 3 shared benchmarks.
General Evaluation
Gemma 4 31B 1/1| Benchmark | Muse Glimmer-30B | Gemma 4 31B | Diff |
|---|---|---|---|
| GPQA Diamond | 83.5098 / 226Thinking High (No Tools) | 84.3093 / 226Thinking (No Tools) | -0.80 |
General Knowledge
Gemma 4 31B 1/1| Benchmark | Muse Glimmer-30B | Gemma 4 31B | Diff |
|---|---|---|---|
| HLE | 22117 / 181Thinking High (No Tools) | 26.50104 / 181Thinking (With Tools + Internet) | -4.50 |
Math and Reasoning
Muse Glimmer-30B 1/1| Benchmark | Muse Glimmer-30B | Gemma 4 31B | Diff |
|---|---|---|---|
| AIME 2026 | 94.706 / 19Thinking High (No Tools) | 89.2016 / 19Thinking (No Tools) | +5.50 |
Specs
| Field | Muse Glimmer-30B | Gemma 4 31B |
|---|---|---|
| Publisher | Facebook AI研究实验室 | DeepMind |
| Release date | 2026-08-10 | 2026-04-02 |
| Model type | Reasoning model | Chat model |
| Architecture | Dense | Dense |
| Parameters | 29.6B | 30.7B |
| Context length | 128K+ | 256K |
| Max output | Not available | 32K |
Summary
- Muse Glimmer-30Bleads in:Math and Reasoning (1/1)
- Gemma 4 31Bleads in:General Evaluation (1/1), General Knowledge (1/1)
On average across the 3 shared benchmarks, Muse Glimmer-30B scores 0.07 higher.
Largest single-benchmark gap: AIME 2026 — Muse Glimmer-30B 94.70 vs Gemma 4 31B 89.20 (+5.50).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.