Model comparison
Claude 3.5 Haiku vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.5 to 28.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 18.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 73.3% for Qwen3 Max.
Side by side
| Claude 3.5 Haiku | Qwen3 Max | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 28.9 | 43.5 |
| Released | 2024-10-22 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.20 |
| Output $ / M tokens | — | $6 |
| Results tracked | 49 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Claude 3.5 Haiku: 32.6 (#258), Qwen3 Max: 42.4 (#93)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1287 | 1456 |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 27.7 (#90), Qwen3 Max: —
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| BALROG | 19.3% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
Claude 3.5 Haiku: 17.1 (#286), Qwen3 Max: 22.0 (#186)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1448 |
| DTBench | 56.7% | 82.1% |
| Epoch Capabilities Index | 127.15 | 142.41 |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| CritPt | 0% | — |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 5% |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 28.3% |
| LiveBench | 43.5% | — |
Math Qwen3 Max leads
Claude 3.5 Haiku: 13.7 (#294), Qwen3 Max: 37.6 (#94)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 73.3% |
| LMArena Math | 1244 | 1447 |
| MATH Level 5 | 46.4% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Qwen3 Max leads
Claude 3.5 Haiku: 18.7 (#276), Qwen3 Max: 48.1 (#72)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 38.1% | 72.6% |
| LMArena Expert | 1208 | 1457 |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.3 (#113), Qwen3 Max: —
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Qwen3 Max leads
Claude 3.5 Haiku: 40.2 (#213), Qwen3 Max: 53.9 (#58)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1238 | 1429 |
| LMArena Chinese | 1229 | 1479 |
| LMArena French | 1262 | 1450 |
| LMArena German | 1237 | 1463 |
| LMArena Japanese | 1175 | 1399 |
| LMArena Korean | 1172 | 1397 |
| LMArena Russian | 1253 | 1428 |
| LMArena Spanish | 1261 | 1463 |
Instruction Following Qwen3 Max leads
Claude 3.5 Haiku: 63.1 (#229), Qwen3 Max: 75.0 (#81)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1241 | 1420 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Qwen3 Max leads
Claude 3.5 Haiku: 38.3 (#195), Qwen3 Max: 41.6 (#129)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1261 | 1439 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Claude 3.5 Haiku: 42.9 (#228), Qwen3 Max: 62.6 (#72)
| Benchmark | Claude 3.5 Haiku | Qwen3 Max |
|---|---|---|
| LMArena Text | 1255 | 1439 |
| LMArena Creative Writing | 1233 | 1401 |
| LMArena Multi-Turn | 1265 | 1446 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.5 to 28.9 on the Noometry Index.
Is Claude 3.5 Haiku or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 42.4 versus 32.6 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Qwen3 Max share?
22 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Qwen3 Max has 33.