Model comparison
Claude Haiku 4.5 vs Qwen2.5 7B Instruct
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 6.5× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Qwen2.5 7B Instruct in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.7% for Claude Haiku 4.5 and 2.5% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 131K.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 29.0 |
| Released | 2025-10-15 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 200K | 131K |
| Max output | 64K | 8K |
| Input $ / M tokens | $1 | $0.17 |
| Output $ / M tokens | $5 | $0.70 |
| Results tracked | 53 | 15 |
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), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1453 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | 31.2% | 7.8% |
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Too close to call
Claude Haiku 4.5: 15.1 (#320), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 8% | 0% |
| DTBench | 73.6% | 47.7% |
| LMCA | 30.9% | 6.4% |
| Epoch Capabilities Index | 142.41 | 118.51 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1420 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 2.5% |
| Omni-MATH | 56.1% | 29.4% |
| LMArena Math | 1396 | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 71.2% | 35.5% |
| MMLU-Pro | 77.7% | 53.9% |
| GPQA (HELM) | 60.5% | 34.1% |
| SimpleQA Verified | 13.2% | — |
| Vectara Hallucination Rate | 9.8% | — |
| LMArena Expert | 1442 | — |
| MMLU | — | 72.9% |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Qwen2.5 7B Instruct: —
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Not comparable
Claude Haiku 4.5: 49.9 (#129), Qwen2.5 7B Instruct: —
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1377 | — |
| LMArena Chinese | 1417 | — |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Russian | 1381 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | 80.1% | 74.1% |
| LMArena Instruction Following | 1414 | — |
Long Context Not comparable
Claude Haiku 4.5: 43.6 (#92), Qwen2.5 7B Instruct: —
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1427 | — |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Claude Haiku 4.5 | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | 83.9% | 73.1% |
| LMArena Text | 1396 | — |
| LMArena Creative Writing | 1372 | — |
| EQ-Bench 4 | 1064 | — |
| LMArena Multi-Turn | 1409 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Qwen2.5 7B Instruct?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 6.5× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Haiku 4.5 or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Qwen2.5 7B Instruct better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 131K.
How many benchmarks do Claude Haiku 4.5 and Qwen2.5 7B Instruct share?
12 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Qwen2.5 7B Instruct has 15.