Model comparison
Claude 3.5 Haiku vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.5-Pro leads 40.0 to 14.7.
- The biggest single-benchmark swing is DTBench: 56.7% for Claude 3.5 Haiku and 84.5% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 29.2 | 45.2 |
| Released | 2024-10-22 | 2026-04-22 |
| Weights | Proprietary | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 49 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 32.9 (#265), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 27.4% | 50.2% |
| LMArena Coding | 1286 | 1503 |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1479 |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 899.8 |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), MiMo-V2.5-Pro: —
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 17.7 (#290), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0% | 4% |
| LMArena Hard Prompts | 1251 | 1488 |
| DTBench | 56.7% | 84.5% |
| NYT Connections (extended) | — | 34.4% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |
Math MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 14.7 (#300), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1244 | 1481 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| ProofBench | — | 22% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 18.7 (#281), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1208 | 1503 |
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), MiMo-V2.5-Pro: —
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 40.0 (#218), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1238 | 1449 |
| LMArena Chinese | 1229 | 1507 |
| LMArena French | 1264 | 1488 |
| LMArena German | 1237 | 1458 |
| LMArena Japanese | 1175 | 1412 |
| LMArena Korean | 1173 | 1437 |
| LMArena Russian | 1253 | 1450 |
| LMArena Spanish | 1261 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 62.9 (#234), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1241 | 1477 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 38.3 (#200), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1261 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Claude 3.5 Haiku: 42.7 (#234), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Claude 3.5 Haiku | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1255 | 1465 |
| LMArena Creative Writing | 1233 | 1440 |
| EQ-Bench Creative Writing | 1146 | 1493 |
| LMArena Multi-Turn | 1265 | 1477 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 76% | — |
| EQ-Bench 4 | — | 1208 |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and MiMo-V2.5-Pro share?
21 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and MiMo-V2.5-Pro has 27.