Model comparison
Mercury 2.5 vs Qwen3.8 Max
Qwen3.8 Max has enough public results to be ranked (#21); Mercury 2.5 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Mercury 2.5 scores higher in 0 categories and Qwen3.8 Max in 1 category; one gap is clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 22.4.
- 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 | 30.2 | 56.0 |
| 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 | 2 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mercury 2.5: —, Qwen3.8 Max: 52.3 (#30)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1671 |
| FrontierSWE | — | 15.8% |
| SciCode | — | 52.9% |
| LMArena Coding | — | 1499 |
| ALE-Bench | 301.65 | — |
Agentic & Tool Use Not comparable
Mercury 2.5: —, Qwen3.8 Max: 42.6 (#17)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Not comparable
Mercury 2.5: —, Qwen3.8 Max: 53.4 (#26)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LMArena Hard Prompts | — | 1493 |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.69 |
Math Qwen3.8 Max leads
Mercury 2.5: 22.4, Qwen3.8 Max: 73.1 (#15)
| 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 | — | 1498 |
Knowledge Not comparable
Mercury 2.5: —, Qwen3.8 Max: 61.7 (#25)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1504 |
Multimodal Not comparable
Mercury 2.5: —, Qwen3.8 Max: 36.9 (#70)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Not comparable
Mercury 2.5: —, Qwen3.8 Max: 56.6 (#18)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | — | 1468 |
| LMArena Chinese | — | 1537 |
| LMArena French | — | 1502 |
| LMArena German | — | 1489 |
| LMArena Japanese | — | 1466 |
| LMArena Korean | — | 1467 |
| LMArena Russian | — | 1478 |
| LMArena Spanish | — | 1495 |
Instruction Following Not comparable
Mercury 2.5: —, Qwen3.8 Max: 77.7 (#19)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | — | 1478 |
Long Context Not comparable
Mercury 2.5: —, Qwen3.8 Max: 45.5 (#30)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | — | 1486 |
Writing & Preference Not comparable
Mercury 2.5: —, Qwen3.8 Max: 67.0 (#31)
| Benchmark | Mercury 2.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | — | 1480 |
| LMArena Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1487 |
Frequently asked questions
Is Mercury 2.5 better than Qwen3.8 Max?
Qwen3.8 Max has enough public results to be ranked (#21); Mercury 2.5 does not yet, so treat this comparison as directional.
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.
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?
1 benchmark has published results for both models. Mercury 2.5 has 2 scored results on Noometry and Qwen3.8 Max has 38.