Model comparison
Claude Haiku 4.5 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 39.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and Qwen3.5 Max Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 30.8 to 15.1.
Side by side
| Claude Haiku 4.5 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 45.3 |
| Released | 2025-10-15 | — |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Haiku 4.5: 44.0 (#78), Qwen3.5 Max Preview: 44.0 (#77)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1453 | 1487 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Qwen3.5 Max Preview: —
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| 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 Qwen3.5 Max Preview leads
Claude Haiku 4.5: 15.1 (#320), Qwen3.5 Max Preview: 30.8 (#84)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1483 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Qwen3.5 Max Preview: 40.1 (#94)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1396 | 1474 |
| 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 Qwen3.5 Max Preview leads
Claude Haiku 4.5: 37.7 (#153), Qwen3.5 Max Preview: 41.8 (#107)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1442 | 1489 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Qwen3.5 Max Preview: —
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Qwen3.5 Max Preview leads
Claude Haiku 4.5: 49.9 (#129), Qwen3.5 Max Preview: 56.2 (#22)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1377 | 1465 |
| LMArena Chinese | 1417 | 1534 |
| LMArena French | 1408 | 1484 |
| LMArena German | 1375 | 1487 |
| LMArena Japanese | 1339 | 1495 |
| LMArena Korean | 1347 | 1438 |
| LMArena Russian | 1381 | 1471 |
| LMArena Spanish | 1420 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
Claude Haiku 4.5: 71.4 (#149), Qwen3.5 Max Preview: 77.0 (#31)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1414 | 1467 |
| IFEval | 80.1% | — |
Long Context Qwen3.5 Max Preview leads
Claude Haiku 4.5: 43.6 (#92), Qwen3.5 Max Preview: 45.2 (#45)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1427 | 1476 |
Writing & Preference Qwen3.5 Max Preview leads
Claude Haiku 4.5: 57.9 (#123), Qwen3.5 Max Preview: 66.0 (#41)
| Benchmark | Claude Haiku 4.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1396 | 1470 |
| LMArena Creative Writing | 1372 | 1464 |
| LMArena Multi-Turn | 1409 | 1478 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 39.5 on the Noometry Index.
Is Claude Haiku 4.5 or Qwen3.5 Max Preview better for coding?
They score almost the same on coding (44.0 vs 44.0); test both on your own repository before choosing.
How many benchmarks do Claude Haiku 4.5 and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Qwen3.5 Max Preview has 17.