MiMo-V2-Flash
Best configuration ranks #224 of 610 on the BenchLeader Index at 53.4 ±5.8 (thinking reasoning effort). Last measured 8 Sept 2026. Released 16 Dec 2025.
- Blended price
- $0.150/M
- $0.100 in · $0.300 out
- Output speed
- –
- First answer
- –
- Context
- 256k
- Overall index53
- Reasoning58
- Coding42
- Agents & tools58
- Knowledge43
- Instruction following63
- Human preference57
- Long context62
- Composite55
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | – | – | – | – | $0.0001 | Coding 45 · Human preference 57 · Reasoning 58 |
| thinkingbest | 53.4 | #224 | – | – | $0.0001 | Agents & tools 58 · Coding 42 · Composite 55 · Human preference 57 · Instruction following 63 · Knowledge 43 · Long context 62 · Reasoning 58 |
| default | 53.3 | #228 | – | – | $0.0001 | Agents & tools 61 · Coding 25 · Composite 57 · Instruction following 70 · Knowledge 55 · Long context 62 |
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1414#139 | 1411#144 | – | LMArena | |
| GPQA Diamond (AA)not in index | – | 84.7%#134 | 83.5%#154 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | – | 22.9%#145 | 22.1%#149 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | – | – | 59.3%#106 | Vals AI |
Coding
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| SciCode | – | – | 25.9%#148 | SciCode | |
| LMArena Coding | 1446#130 | 1430#153 | – | LMArena | |
| LMArena WebDev | 1331#96 | 1293#100 | – | LMArena |
Agents & tools
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| Terminal-Bench Hard | – | 28.0%#122 | 31.1%#104 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | – | 95.0%#27 | 93.3%#44 | Artificial Analysis |
Knowledge
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| AA-Omniscience | – | -45.4#285 | -19.1#179 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| IFBench | – | 64.2%#110 | 71.8%#51 | Artificial Analysis |
Human preference
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| LMArena Text | 1392#139 | 1386#147 | – | LMArena |
Long context
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| AA-LCR | – | 70.7%#154 | 71.3%#149 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | default | Source | Trend |
|---|---|---|---|---|---|
| AA Intelligence Index | – | 20.8#166 | 22.4#144 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.300 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | $0.0002 | – |
| Summarise a 30-page report | 12,000 / 600 | $0.0014 | $0.0032 | – |
| Code edit | 6,000 / 1,500 | $0.0011 | $0.0019 | – |
| Agentic coding session | 60,000 / 4,000 | $0.0072 | $0.016 | – |
| Structured extraction | 2,000 / 200 | $0.0003 | $0.0006 | – |
See also
Data as of 9 Sept 2026. Compare these configurations.