Model comparison
Qwen2.5 7B Instruct vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 9.8× less per token, which makes it the better buy when Qwen3.8 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 Qwen3.8 Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Qwen2.5 7B Instruct and 100% for Qwen3.8 Max.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 131K.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 7B Instruct | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.0 | 56.8 |
| Released | 2024-09 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.17 | $2 |
| Output $ / M tokens | $0.70 | $6 |
| Results tracked | 15 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen2.5 7B Instruct: 36.5 (#208), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1502 |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Qwen3.8 Max leads
Qwen2.5 7B Instruct: 23.8 (#124), Qwen3.8 Max: 45.4 (#14)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| BALROG | 7.8% | — |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Qwen2.5 7B Instruct: 14.8 (#322), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| Chess Puzzles | 0% | 40% |
| DTBench | 47.7% | 92% |
| LMCA | 6.4% | 46.2% |
| Epoch Capabilities Index | 118.51 | 156.41 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
Math Qwen3.8 Max leads
Qwen2.5 7B Instruct: 12.6 (#306), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 100% |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1499 |
Knowledge Qwen3.8 Max leads
Qwen2.5 7B Instruct: 17.0 (#286), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 35.5% | 92.7% |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1507 |
| MMLU | 72.9% | — |
Multimodal Not comparable
Qwen2.5 7B Instruct: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Qwen3.8 Max: 56.7 (#18)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1472 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Russian | — | 1481 |
| LMArena Spanish | — | 1492 |
Instruction Following Qwen3.8 Max leads
Qwen2.5 7B Instruct: 63.2 (#231), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1479 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Qwen3.8 Max: 45.6 (#31)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |
Writing & Preference Qwen3.8 Max leads
Qwen2.5 7B Instruct: 48.8 (#195), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Qwen2.5 7B Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1489 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 9.8× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen2.5 7B Instruct or Qwen3.8 Max?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Qwen2.5 7B Instruct or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 131K.
How many benchmarks do Qwen2.5 7B Instruct and Qwen3.8 Max share?
6 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Qwen3.8 Max has 39.