Model comparison
Claude Haiku 4.5 vs Qwen3-Coder 480B-A35B Instruct
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 38.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Qwen3-Coder 480B-A35B Instruct in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-Coder 480B-A35B Instruct leads 25.5 to 15.1.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 66.6% for Claude Haiku 4.5 and 55.4% for Qwen3-Coder 480B-A35B Instruct.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 200K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 38.1 |
| Released | 2025-10-15 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $1 | $1.50 |
| Output $ / M tokens | $5 | $7.50 |
| Results tracked | 53 | 25 |
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-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 66.6% | 55.4% |
| LMArena WebDev | 1330 | 1275 |
| WeirdML | 45.4% | 41.2% |
| LMArena Coding | 1453 | 1412 |
| ALE-Bench | 653.48 | 461.45 |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | 35.5% | 27.2% |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Claude Haiku 4.5: 15.1 (#320), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1372 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | — | 49.5% |
| 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-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1396 | 1365 |
| 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 Too close to call
Claude Haiku 4.5: 37.7 (#153), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1442 | 1338 |
| 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-Coder 480B-A35B Instruct: —
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1377 | 1346 |
| LMArena Chinese | 1417 | 1357 |
| LMArena French | 1408 | 1398 |
| LMArena German | 1375 | 1325 |
| LMArena Japanese | 1339 | 1310 |
| LMArena Korean | 1347 | 1305 |
| LMArena Russian | 1381 | 1366 |
| LMArena Spanish | 1420 | 1360 |
Instruction Following Too close to call
Claude Haiku 4.5: 71.4 (#149), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1414 | 1355 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1427 | 1378 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Claude Haiku 4.5 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1396 | 1357 |
| LMArena Creative Writing | 1372 | 1333 |
| LMArena Multi-Turn | 1409 | 1365 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Qwen3-Coder 480B-A35B Instruct?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 38.1 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or Qwen3-Coder 480B-A35B Instruct?
Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Claude Haiku 4.5 or Qwen3-Coder 480B-A35B Instruct better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Qwen3-Coder 480B-A35B Instruct share?
22 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.