# Claude 3 Haiku vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen3.7 Plus in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 49.3 to 9.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 93.3% for Qwen3.7 Plus.

## Snapshot

| | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.7 | 45.0 |
| Rank | 333 | 66 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1199 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1460 |
| DTBench | 50.1% | 84% |
| LMCA | 8.8% | 37.6% |
| Epoch Capabilities Index | 118.3 | 147.39 |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 93.3% |
| LMArena Math | 1188 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 36.3% | 87.9% |
| LMArena Expert | 1148 | 1467 |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 950 | 1281 |
| LMArena Document | — | 1444 |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1178 | 1445 |
| LMArena Chinese | 1155 | 1510 |
| LMArena French | 1194 | 1471 |
| LMArena German | 1174 | 1471 |
| LMArena Japanese | 1102 | 1411 |
| LMArena Korean | 1108 | 1416 |
| LMArena Russian | 1204 | 1457 |
| LMArena Spanish | 1165 | 1453 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1174 | 1439 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1191 | 1454 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Claude 3 Haiku | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1195 | 1454 |
| LMArena Creative Writing | 1157 | 1439 |
| LMArena Multi-Turn | 1190 | 1459 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Qwen3.7 Plus better for coding?

Qwen3.7 Plus scores higher on coding benchmarks: 36.1 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Qwen3.7 Plus share?

23 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3.7 Plus has 32.