MiMo-V2.6 Flash: benchmark scores, price and ranking
MiMo-V2.6 Flash from Xiaomi Corp ranks #100 of 743 LLMs on the LLMs Tiger aggregate benchmark score (51.7), based on 4 benchmark results captured up to 2026-10-13.
- Organisation
- Xiaomi Corp
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2026-09-21 (source: epoch)
- Cheapest API price
- $0.140 in / $0.280 out per million tokens (via openrouter, observed 2026-10-13T20:47Z)
- Aggregate rank
- #100 of 743 (score 51.7)
Relative to other models, MiMo-V2.6 Flash is strongest on ProofBench (#10 of 46) and weakest on LMArena Code Elo (#11 of 30).
Across the 4 benchmarks where at least ten models are scored, MiMo-V2.6 Flash is in the top 10% on 0 and in the top half on 4.
Its cheapest listed input price, $0.140 per million tokens, is lower than that of 75% of the 427 models with a listed price.
MiMo-V2.6 Flash benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| ProofBench | 63.0% | #10 of 46 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 51.3% | #32 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 12.0% | #36 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMArena Code Elo | 1,636 | #11 of 30 | LMArena | 2026-10-13 |
About MiMo-V2.6 Flash
MiMo-V2.6 Flash is an open-weight model that can run on your own hardware from Xiaomi Corp. It was released on 2026-09-21, according to Epoch AI. The cheapest API listing we track charges $0.140 per million input tokens and $0.280 per million output tokens, through openrouter. We hold 4 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where MiMo-V2.6 Flash stands
On our aggregate score, MiMo-V2.6 Flash is #100 of 743 ranked models, in the top quarter. Its score is 51.7; the scale is centred on 50, so it sits 1.7 points above the typical model. That beats 87% of the ranked field. Among the 5 ranked Xiaomi Corp models it is #2. The next one up is mimo-v2.6-pro at 54.7. The next one down is mimo-v2.5-pro at 49.5.
MiMo-V2.6 Flash, benchmark by benchmark
ProofBench puts MiMo-V2.6 Flash at 63.0%, #10 of 46. That beats 78% of the models tested, but 37.0 points short of Claude Fable 5.1 (max) (100.0%). The results either side are mimo-v2.6-pro (70.0%) and GPT-5.6 Luna (max) (60.0%). It covers writing mathematical proofs. The board median is 21.0%, so MiMo-V2.6 Flash is 42.0 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On SciCode, MiMo-V2.6 Flash reaches 51.3%. It ranks #32 of 106, ahead of 70% of the field, and 15.6 points behind Claude Opus 5.5 (max) at 66.9%. The results either side are Muse Spark (51.5%) and DeepSeek V4 Pro 0813 (max) (51.0%). It covers scientific research code. The board median is 44.3%, so MiMo-V2.6 Flash is 6.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
MiMo-V2.6 Flash manages 12.0% on CritPt, good for #36 of 115. GPT-5.6 Sol (max) leads at 32.3%, 20.3 points further up, and 69% of models sit below. The results either side are Claude Opus 4.7 (max) (12.0%) and Muse Spark (11.3%). It covers unpublished research-level physics problems. The board median is 2.9%, so MiMo-V2.6 Flash is 9.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMArena Code Elo puts MiMo-V2.6 Flash at 1,636, #11 of 30. That beats 63% of the models tested, but 178 points short of Claude Opus 5.5 (max) (1,814). The results either side are Grok 4.7 (xhigh) (1,638) and Hy4-preview (1,632). It covers crowd-voted coding answers. The board median is 1,622, so MiMo-V2.6 Flash is 14 points above it. Source: LMArena, captured 2026-10-13.
Strengths and weaknesses
Software engineering: solid, ahead of 67% of the field on average across 2 benchmarks. Its best board here is SciCode (#32 of 106) and its weakest is LMArena Code Elo (#11 of 30). Reasoning, maths and science: solid, ahead of 73% of the field on average across 2 benchmarks. Its best board here is ProofBench (#10 of 46) and its weakest is CritPt (#36 of 115).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so MiMo-V2.6 Flash costs less than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4 Flash 0731 (max) ($0.016, 53.1), Qwen3.7 Flash ($0.030, 50.5), GLM-5.2 (high) ($0.060, 51.6). Similar scores cost more on Qwen3.5 397B-A17B ($0.164) and grok-4-1-fast-non-reasoning ($0.200).
Release history
The Xiaomi Corp model released before it was mimo-v2.5-pro on 2026-04-22, which scores 49.5. The next one was mimo-v2.6-pro on 2026-09-21, at 54.7.
Reading these numbers
The 4 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (3), LMArena (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 4 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #97 GPT-4 (0806) (51.8)
- #98 Kimi K2 (51.8)
- #99 Ornith-1.5-35B-A3B (51.8)
- #101 DeepSeek-V2.5-1210 (51.7)
- #102 openai/chatgpt-4o-latest (51.7)
- #103 Darwin-36B-Opus (51.7)
More from Xiaomi Corp
- mimo-v2.6-pro (#19, 54.7)
- mimo-v2.5-pro (#259, 49.5)
- mimo-v2.5 (#494, 46.7)
- mimo-v2-pro (#502, 46.6)
Compare it on the live leaderboard → · How the aggregate score works