Model comparison
Claude 3 Haiku vs MiMo-V2.6-Pro
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 25.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and MiMo-V2.6-Pro in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 9.8.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 25.9 | 50.3 |
| Released | 2024-03-07 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 37 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
Claude 3 Haiku: 26.4 (#325), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Coding | 1199 | 1534 |
| LMArena WebDev | — | 1629 |
| SciCode | — | 60.9% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 1,158 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | — | 59.5% |
Reasoning MiMo-V2.6-Pro leads
Claude 3 Haiku: 16.3 (#307), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1512 |
| Kagi LLM Benchmark | 34.2% | — |
| CritPt | — | 26.6% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math MiMo-V2.6-Pro leads
Claude 3 Haiku: 9.8 (#319), MiMo-V2.6-Pro: 54.5 (#45)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Math | 1188 | 1494 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| ProofBench | — | 70% |
| MATH Level 5 | 14.9% | — |
Knowledge MiMo-V2.6-Pro leads
Claude 3 Haiku: 17.3 (#285), MiMo-V2.6-Pro: 43.5 (#92)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1148 | 1543 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal MiMo-V2.6-Pro leads
Claude 3 Haiku: 23.6 (#128), MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 950 | 1264 |
| ScienceQA | 72% | — |
Multilingual MiMo-V2.6-Pro leads
Claude 3 Haiku: 36.0 (#243), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1178 | 1474 |
| LMArena Chinese | 1155 | 1529 |
| LMArena Russian | 1204 | 1480 |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Spanish | 1166 | — |
Instruction Following MiMo-V2.6-Pro leads
Claude 3 Haiku: 61.3 (#247), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1173 | 1493 |
Long Context MiMo-V2.6-Pro leads
Claude 3 Haiku: 36.1 (#237), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1190 | 1501 |
Writing & Preference MiMo-V2.6-Pro leads
Claude 3 Haiku: 29.7 (#291), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | Claude 3 Haiku | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1195 | 1492 |
| LMArena Creative Writing | 1157 | 1468 |
| LMArena Multi-Turn | 1190 | 1464 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and MiMo-V2.6-Pro share?
13 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and MiMo-V2.6-Pro has 19.