mimo-v2.6-pro: benchmark scores, price and ranking
mimo-v2.6-pro from Xiaomi Corp ranks #22 of 743 LLMs on the LLMs Tiger aggregate benchmark score (54.5), based on 8 benchmark results captured up to 2026-10-06.
- Organisation
- Xiaomi Corp
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2026-09-21 (source: epoch)
- Cheapest API price
- $0.435 in / $0.870 out per million tokens (via openrouter, observed 2026-10-06T01:47Z)
- Aggregate rank
- #22 of 743 (score 54.5)
Relative to other models, mimo-v2.6-pro is strongest on SciCode (#6 of 106) and weakest on LMArena Code Elo (#16 of 29).
mimo-v2.6-pro benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| SciCode | 60.9% | #6 of 106 | Epoch AI Benchmarking Hub | 2026-10-06 |
| CritPt | 26.6% | #15 of 117 | Epoch AI Benchmarking Hub | 2026-10-06 |
| WebDev Arena | 1,618 | #11 of 67 | Epoch AI Benchmarking Hub | 2026-10-06 |
| ProofBench | 70.0% | #9 of 46 | Epoch AI Benchmarking Hub | 2026-10-06 |
| ALE-Bench | 1,158 | #21 of 79 | Epoch AI Benchmarking Hub | 2026-10-06 |
| APEX-Agents | 59.5% | #5 of 17 | Epoch AI Benchmarking Hub | 2026-10-06 |
| LMArena Text Elo | 1,480 | #13 of 28 | LMArena | 2026-10-06 |
| LMArena Code Elo | 1,618 | #16 of 29 | LMArena | 2026-10-06 |
Models ranked nearby
- #19 gemini-3.1-pro-preview-high (55.3)
- #20 GPT-5.6 Luna (max) (55.1)
- #21 Muse Spark 1.3 (max) (55.0)
- #23 Claude 4 Sonnet (54.5)
- #24 Claude 4.5 Opus (54.5)
- #25 Claude 3.5-Sonnet-20241022 (54.4)
Compare it on the live leaderboard → · How the aggregate score works