Model comparison
Claude Haiku 4.5 vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 39.5 on the Noometry Index.
Last verified . 32 shared benchmarks.
Alibaba (Qwen)Summary
- They share 32 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and Qwen3.6 Plus in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 37.7.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 60.3% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Qwen3.6 Plus accepts more context: 1M tokens versus 200K.
Side by side
| Claude Haiku 4.5 | Qwen3.6 Plus | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 47.5 |
| Released | 2025-10-15 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 64K | 66K |
| Input $ / M tokens | $1 | $0.50 |
| Output $ / M tokens | $5 | $3 |
| Results tracked | 53 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1330 | 1461 |
| SciCode | 43.3% | 40.7% |
| LMArena Coding | 1453 | 1467 |
| ALE-Bench | 653.48 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| WeirdML | 45.4% | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Qwen3.6 Plus: —
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 458.89 | 5,115 |
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
Reasoning Qwen3.6 Plus leads
Claude Haiku 4.5: 15.1 (#320), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 14.3% | 60.3% |
| CritPt | 0% | 2.9% |
| Chess Puzzles | 8% | 17% |
| LMArena Hard Prompts | 1420 | 1449 |
| DTBench | 73.6% | 81.9% |
| LMCA | 30.9% | 33.1% |
| Epoch Capabilities Index | 142.41 | 147.65 |
| ARC-AGI-2 | 4% | — |
| ARC-AGI-1 | 47.7% | — |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| ForecastBench | 61.4 | — |
Math Qwen3.6 Plus leads
Claude Haiku 4.5: 44.9 (#78), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 93.3% |
| LMArena Math | 1396 | 1450 |
| FrontierMath (Feb 2025 set) | 5.9% | 26.2% |
| FrontierMath Tier 4 (v1) | 2.1% | 8.3% |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
Knowledge Qwen3.6 Plus leads
Claude Haiku 4.5: 37.7 (#153), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 71.2% | 88.4% |
| SimpleQA Verified | 13.2% | 44.1% |
| LMArena Expert | 1442 | 1454 |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Qwen3.6 Plus: —
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Qwen3.6 Plus leads
Claude Haiku 4.5: 49.9 (#129), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1377 | 1424 |
| LMArena Chinese | 1417 | 1477 |
| LMArena French | 1408 | 1455 |
| LMArena German | 1375 | 1452 |
| LMArena Japanese | 1339 | 1389 |
| LMArena Korean | 1347 | 1379 |
| LMArena Russian | 1381 | 1434 |
| LMArena Spanish | 1420 | 1432 |
Instruction Following Qwen3.6 Plus leads
Claude Haiku 4.5: 71.4 (#149), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1414 | 1425 |
| IFEval | 80.1% | — |
Long Context Qwen3.6 Plus leads
Claude Haiku 4.5: 43.6 (#92), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1427 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
Claude Haiku 4.5: 57.9 (#123), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Claude Haiku 4.5 | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1396 | 1437 |
| LMArena Creative Writing | 1372 | 1404 |
| LMArena Multi-Turn | 1409 | 1438 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or Qwen3.6 Plus?
Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Qwen3.6 Plus better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Qwen3.6 Plus share?
32 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Qwen3.6 Plus has 37.