Model comparison
Claude 3 Haiku vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 25.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 9.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 91.1% for Qwen3.6 Max Preview.
Side by side
| Claude 3 Haiku | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.9 | 51.5 |
| Released | 2024-03-07 | 2026-04-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.30 |
| Output $ / M tokens | — | $7.80 |
| Results tracked | 37 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Claude 3 Haiku: 26.4 (#325), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1199 | 1471 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Agentic & Tool Use Not comparable
Claude 3 Haiku: —, Qwen3.6 Max Preview: —
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Claude 3 Haiku: 16.3 (#307), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1457 |
| DTBench | 50.1% | 87.2% |
| LMCA | 8.8% | 42.5% |
| Epoch Capabilities Index | 118.35 | 149.24 |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 74.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math Qwen3.6 Max Preview leads
Claude 3 Haiku: 9.8 (#319), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 91.1% |
| LMArena Math | 1188 | 1465 |
| MATH Level 5 | 14.9% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Claude 3 Haiku: 17.3 (#285), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 36.3% | 87.4% |
| LMArena Expert | 1148 | 1478 |
| SimpleQA Verified | — | 52% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), Qwen3.6 Max Preview: —
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Qwen3.6 Max Preview leads
Claude 3 Haiku: 36.0 (#243), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1178 | 1437 |
| LMArena Chinese | 1155 | 1487 |
| LMArena French | 1195 | 1449 |
| LMArena Russian | 1204 | 1445 |
| LMArena Spanish | 1166 | 1454 |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
Instruction Following Qwen3.6 Max Preview leads
Claude 3 Haiku: 61.3 (#247), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1173 | 1438 |
Long Context Qwen3.6 Max Preview leads
Claude 3 Haiku: 36.1 (#237), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1190 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
Claude 3 Haiku: 29.7 (#291), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Claude 3 Haiku | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1195 | 1447 |
| LMArena Creative Writing | 1157 | 1435 |
| LMArena Multi-Turn | 1190 | 1456 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Qwen3.6 Max Preview share?
19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3.6 Max Preview has 29.