Model comparison
Qwen2.5 7B Instruct vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 7.8× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Qwen2.5 7B Instruct scores higher in 0 categories and Qwen3 Max in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 17.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Qwen2.5 7B Instruct and 73.3% for Qwen3 Max.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 131K.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 7B Instruct | Qwen3 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.0 | 43.7 |
| Released | 2024-09 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.17 | $1.20 |
| Output $ / M tokens | $0.70 | $6 |
| Results tracked | 15 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Qwen2.5 7B Instruct: 36.5 (#208), Qwen3 Max: 43.0 (#93)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1456 |
| BigCodeBench Complete | 46.1% | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.8 (#124), Qwen3 Max: —
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| BALROG | 7.8% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
Qwen2.5 7B Instruct: 14.8 (#322), Qwen3 Max: 22.6 (#190)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| Chess Puzzles | 0% | 4% |
| DTBench | 47.7% | 82.1% |
| LMCA | 6.4% | 28.3% |
| Epoch Capabilities Index | 118.51 | 142.38 |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| LMArena Hard Prompts | — | 1448 |
| Mystery Game Puzzles | — | 5% |
Math Qwen3 Max leads
Qwen2.5 7B Instruct: 12.6 (#306), Qwen3 Max: 38.7 (#131)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 73.3% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1446 |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
Qwen2.5 7B Instruct: 17.0 (#286), Qwen3 Max: 48.1 (#78)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 35.5% | 72.6% |
| SimpleQA Verified | — | 48.7% |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1455 |
| MMLU | 72.9% | — |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Qwen3 Max: 53.7 (#62)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| LMArena Non-English | — | 1429 |
| LMArena Chinese | — | 1478 |
| LMArena French | — | 1449 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1397 |
| LMArena Korean | — | 1399 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1462 |
Instruction Following Qwen3 Max leads
Qwen2.5 7B Instruct: 63.2 (#231), Qwen3 Max: 74.8 (#87)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1419 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Qwen3 Max: 41.6 (#134)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
| LMArena Longer Query | — | 1438 |
Writing & Preference Qwen3 Max leads
Qwen2.5 7B Instruct: 48.8 (#195), Qwen3 Max: 62.4 (#76)
| Benchmark | Qwen2.5 7B Instruct | Qwen3 Max |
|---|---|---|
| LMArena Text | — | 1439 |
| LMArena Creative Writing | — | 1402 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1446 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 7.8× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen2.5 7B Instruct or Qwen3 Max?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Qwen2.5 7B Instruct or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 131K.
How many benchmarks do Qwen2.5 7B Instruct and Qwen3 Max share?
6 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen3 Max has 33.