Model comparison
Mercury 2.5 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 44× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Mercury 2.5 scores higher in 0 categories and Qwen3.8 Max in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 23.3.
- The biggest single-benchmark swing is ProofBench: 3% for Mercury 2.5 and 58% for Qwen3.8 Max.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 260K.
Side by side
| Mercury 2.5 | Qwen3.8 Max | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 33.5 | 56.8 |
| Released | 2026-09-08 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 260K | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.04 | $2 |
| Output $ / M tokens | $0.15 | $6 |
| Results tracked | 4 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Mercury 2.5: 39.5 (#156), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| SciCode | 38.5% | 53.2% |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| LMArena Coding | — | 1502 |
| ALE-Bench | 301.65 | — |
Agentic & Tool Use Not comparable
Mercury 2.5: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Mercury 2.5: 22.4 (#193), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| CritPt | 0% | 20% |
| NYT Connections (extended) | — | 88.3% |
| Chess Puzzles | — | 40% |
| LMArena Hard Prompts | — | 1496 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
Mercury 2.5: 23.3 (#272), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| ProofBench | 3% | 58% |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| LMArena Math | — | 1499 |
Knowledge Not comparable
Mercury 2.5: —, Qwen3.8 Max: 61.7 (#27)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |
Multimodal Not comparable
Mercury 2.5: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Mercury 2.5: —, Qwen3.8 Max: 56.7 (#18)
| Benchmark | Mercury 2.5 | 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 Not comparable
Mercury 2.5: —, Qwen3.8 Max: 77.6 (#17)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1479 |
Long Context Not comparable
Mercury 2.5: —, Qwen3.8 Max: 45.6 (#31)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1489 |
Writing & Preference Not comparable
Mercury 2.5: —, Qwen3.8 Max: 67.1 (#30)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1483 |
| LMArena Creative Writing | — | 1479 |
| LMArena Multi-Turn | — | 1489 |
Frequently asked questions
Is Mercury 2.5 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 44× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Mercury 2.5 or Qwen3.8 Max?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Mercury 2.5 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 39.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 260K.
How many benchmarks do Mercury 2.5 and Qwen3.8 Max share?
3 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Qwen3.8 Max has 39.