Compare / head-to-head
MiMo-V2.6-Flashvs
Muse Spark 1.2
MiMo-V2.6-Flash and Muse Spark 1.2 split their 7 shared benchmarks evenly. Muse Spark 1.2 has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 3
even split
Cheaper per token
—
list price, input + output
Larger context
Muse Spark 1.2
1.0M tokens
Providers
2 providers
Xiaomi MiMo · Meta
MiMo-V2.6-Flash
Xiaomi MiMo · released 2026-09-21
textvisionaudiovideo
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 12 · 3 core
Muse Spark 1.2
Meta · released 2026-08-05
textvisionvideoaudio
Quality
Benchmark matrix
7 shared · 5 only MiMo-V2.6-Flash · 16 only Muse Spark 1.2| Benchmark | MiMo-V2.6-Flash | Muse Spark 1.2 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| LMArena Elo | 1451.8 ↗ | 1493.5 ↗ | -41.7 | Muse Spark 1.2 |
| DeepSWE v1.1 | 67.9% ↗ | 59.3% ↗ | +8.6 pt | MiMo-V2.6-Flash |
| LMArena Agent (LMArena) | -0.0057 ↗ | -0.0327 ↗ | 0 | Tie |
| LMArena Vision (LMArena) | 1247.5 ↗ | 1292.8 ↗ | -45.3 | Muse Spark 1.2 |
| SAGE (Vals AI) | 43.5% ↗ | 47.7% ↗ | -4.2 pt | Muse Spark 1.2 |
| Terminal-Bench 2.1 | 87.6% ↗ | 82.9% ↗ | +4.7 pt | MiMo-V2.6-Flash |
| Terminal-Bench 4.0 (Vals AI) | 24.2% ↗ | 6.1% ↗ | +18.1 pt | MiMo-V2.6-Flash |
| Only MiMo-V2.6-Flash reports · 5 | ||||
| Agents' Last Exam | 27.6% ↗ | not reported | — | — |
| AutomationBench 1.0.6 | 52.3% ↗ | not reported | — | — |
| JobBench | 61.2% ↗ | not reported | — | — |
| OSWorld-Verified | 80.8% ↗ | not reported | — | — |
| Terminal-Bench 4.0 | 28.8% ↗ | not reported | — | — |
| Only Muse Spark 1.2 reports · 16 | ||||
| APEX-Agents (Mercor) | not reported | 36.4% ↗ | — | — |
| DeepSWE v1.1 (Datacurve) | not reported | 54.9% ↗ | — | — |
| FrontierSWE V2 (Proximal Labs) | not reported | 12% ↗ | — | — |
| LiveBench Agentic Coding (LiveBench) | not reported | 57.6% ↗ | — | — |
| LiveBench Coding (LiveBench) | not reported | 77.5% ↗ | — | — |
| LiveBench Data Analysis (LiveBench) | not reported | 76.5% ↗ | — | — |
| LiveBench Instruction Following (LiveBench) | not reported | 74.3% ↗ | — | — |
| LiveBench Language (LiveBench) | not reported | 78.6% ↗ | — | — |
| LiveBench Mathematics (LiveBench) | not reported | 91.2% ↗ | — | — |
| LiveBench Reasoning (LiveBench) | not reported | 90% ↗ | — | — |
| LMArena WebDev (LMArena) | not reported | 1531.8 ↗ | — | — |
| MCP Atlas | not reported | 90.3% ↗ | — | — |
| SimpleBench (SimpleBench) | not reported | 74.5% ↗ | — | — |
| SimpleQA Verified | not reported | 60.3% ↗epoch run | — | — |
| Toolathlon-Verified (HKUST) | not reported | 75.9% ↗ | — | — |
| WeirdML (Håvard Tveit Ihle) | not reported | 60.3% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is MiMo-V2.6-Flash minus Muse Spark 1.2 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | MiMo-V2.6-Flash | Muse Spark 1.2 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Muse Spark 1.2 |
| Max output | — | — | — |
| Input price / 1M | — | $1.25 ↗ | — |
| Output price / 1M | — | $4.25 ↗ | — |
| Cached input / 1M | — | $0.15 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $5.5 | — |
| Modalities | text · vision · audio · video | text · vision · video · audio | Tie |
| Released | 2026-09-21 | 2026-08-05 | — |
| Cited benchmark scores | 12 | 23 | — |
Reliability
Provider status
Live from /statusMore matchups
MiMo-V2.6-Flash vs …
Models sharing the most benchmarksMore matchups
Muse Spark 1.2 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run MiMo-V2.6-Flash and Muse Spark 1.2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.