Model comparison
Claude 3 Haiku vs MiMo-V2-Omni
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 25.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and MiMo-V2-Omni in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Omni leads 61.6 to 29.8.
Side by side
| Claude 3 Haiku | MiMo-V2-Omni | |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 25.7 | 42.9 |
| Released | 2024-03-07 | 2026-03-18 |
| Weights | Proprietary | Proprietary |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Omni leads
Claude 3 Haiku: 26.1 (#320), MiMo-V2-Omni: 42.7 (#87)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Coding | 1199 | 1467 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning MiMo-V2-Omni leads
Claude 3 Haiku: 15.7 (#303), MiMo-V2-Omni: 28.6 (#86)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1445 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math MiMo-V2-Omni leads
Claude 3 Haiku: 9.2 (#313), MiMo-V2-Omni: 36.4 (#112)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Math | 1188 | 1432 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge MiMo-V2-Omni leads
Claude 3 Haiku: 17.3 (#280), MiMo-V2-Omni: 39.9 (#114)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Expert | 1148 | 1449 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal MiMo-V2-Omni leads
Claude 3 Haiku: 23.1 (#123), MiMo-V2-Omni: 37.9 (#62)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Vision | 950 | 1228 |
| ScienceQA | 72% | — |
Multilingual MiMo-V2-Omni leads
Claude 3 Haiku: 36.1 (#238), MiMo-V2-Omni: 52.0 (#97)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Non-English | 1178 | 1404 |
| LMArena Chinese | 1155 | 1469 |
| LMArena French | 1194 | 1448 |
| LMArena German | 1174 | 1398 |
| LMArena Japanese | 1102 | 1318 |
| LMArena Korean | 1108 | 1355 |
| LMArena Russian | 1204 | 1412 |
| LMArena Spanish | 1165 | 1432 |
Instruction Following MiMo-V2-Omni leads
Claude 3 Haiku: 61.5 (#242), MiMo-V2-Omni: 75.4 (#62)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Instruction Following | 1174 | 1428 |
Long Context MiMo-V2-Omni leads
Claude 3 Haiku: 36.1 (#232), MiMo-V2-Omni: 44.1 (#72)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Longer Query | 1191 | 1442 |
Writing & Preference MiMo-V2-Omni leads
Claude 3 Haiku: 29.8 (#286), MiMo-V2-Omni: 61.6 (#83)
| Benchmark | Claude 3 Haiku | MiMo-V2-Omni |
|---|---|---|
| LMArena Text | 1195 | 1424 |
| LMArena Creative Writing | 1157 | 1393 |
| LMArena Multi-Turn | 1190 | 1446 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than MiMo-V2-Omni?
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or MiMo-V2-Omni better for coding?
MiMo-V2-Omni scores higher on coding benchmarks: 42.7 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and MiMo-V2-Omni share?
18 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and MiMo-V2-Omni has 18.