# Claude Haiku 4.5 vs MiMo-V2-Pro

> MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 39.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-mimo-v2-pro
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 3 categories and MiMo-V2-Pro in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 43.0 to 36.7.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 25.8% for MiMo-V2-Pro.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 200K.

## Snapshot

| | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 39.3 | 42.4 |
| Rank | 155 | 102 |
| Context | 200K | 1.05M |
| Input $/M | $1 | $0.43 |
| Output $/M | $5 | $0.87 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 4.5: 43.9 (#71)
- MiMo-V2-Pro: 43.4 (#76)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1330 | 1433 |
| LMArena Coding | 1454 | 1476 |
| ALE-Bench | 653.48 | 785.17 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.5 (#50)
- MiMo-V2-Pro: —

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#310)
- MiMo-V2-Pro: 21.3 (#200)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 14.3% | 25.8% |
| LMArena Hard Prompts | 1420 | 1457 |
| ARC-AGI-2 | 4% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| Thematic Generalization | — | 45.9% |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.42 | — |
| ForecastBench | 61.4 | — |

## Math

- Claude Haiku 4.5: 43.0 (#69)
- MiMo-V2-Pro: 36.7 (#104)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1395 | 1447 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Claude Haiku 4.5: 37.6 (#146)
- MiMo-V2-Pro: 40.8 (#106)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1443 | 1479 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 27.0 (#111)
- MiMo-V2-Pro: —

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 50.1 (#124)
- MiMo-V2-Pro: 52.9 (#77)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1376 | 1416 |
| LMArena Chinese | 1415 | 1455 |
| LMArena French | 1408 | 1470 |
| LMArena German | 1377 | 1417 |
| LMArena Japanese | 1339 | 1366 |
| LMArena Korean | 1346 | 1401 |
| LMArena Russian | 1380 | 1427 |
| LMArena Spanish | 1420 | 1458 |

## Instruction Following

- Claude Haiku 4.5: 71.6 (#144)
- MiMo-V2-Pro: 76.2 (#46)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1414 | 1444 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#86)
- MiMo-V2-Pro: 41.5 (#133)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1427 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- Claude Haiku 4.5: 58.1 (#119)
- MiMo-V2-Pro: 62.9 (#67)

| Benchmark | Claude Haiku 4.5 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1396 | 1436 |
| LMArena Creative Writing | 1371 | 1415 |
| LMArena Multi-Turn | 1409 | 1456 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than MiMo-V2-Pro?

MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 39.3 on the Noometry Index.

### Which is cheaper, Claude Haiku 4.5 or MiMo-V2-Pro?

MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

### Is Claude Haiku 4.5 or MiMo-V2-Pro better for coding?

They score almost the same on coding (43.9 vs 43.4); test both on your own repository before choosing.

### Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 200K.

### How many benchmarks do Claude Haiku 4.5 and MiMo-V2-Pro share?

20 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and MiMo-V2-Pro has 23.