Model comparison
Mercury vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 37.6 on the Noometry Index.
Last verified . 9 shared benchmarks.
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. Mercury scores higher in 1 category and Qwen3 32B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 46.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 21.6% for Mercury and 54.9% for Qwen3 32B.
- Qwen3 32B has downloadable open weights; the other is API-only.
Side by side
| Mercury | Qwen3 32B | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 37.6 | 39.2 |
| Released | — | 2025-04 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 9 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury: 38.7 (#170), Qwen3 32B: 37.7 (#190)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1322 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Mercury: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Qwen3 32B leads
Mercury: 17.5 (#293), Qwen3 32B: 20.2 (#241)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 21.6% | 54.9% |
| LMArena Hard Prompts | 1285 | 1334 |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Not comparable
Mercury: —, Qwen3 32B: 39.7 (#99)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LMArena Math | — | 1399 |
Knowledge Not comparable
Mercury: —, Qwen3 32B: 40.0 (#125)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
Multilingual Qwen3 32B leads
Mercury: 41.6 (#206), Qwen3 32B: 45.6 (#167)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1260 | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Qwen3 32B leads
Mercury: 65.2 (#224), Qwen3 32B: 68.9 (#179)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1305 |
Long Context Qwen3 32B leads
Mercury: 38.4 (#198), Qwen3 32B: 43.8 (#87)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1266 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Mercury: 46.2 (#221), Qwen3 32B: 52.9 (#163)
| Benchmark | Mercury | Qwen3 32B |
|---|---|---|
| LMArena Text | 1282 | 1340 |
| LMArena Creative Writing | 1191 | 1297 |
| LMArena Multi-Turn | 1282 | 1331 |
Frequently asked questions
Is Mercury better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 37.6 on the Noometry Index.
Is Mercury or Qwen3 32B better for coding?
They score almost the same on coding (38.7 vs 37.7); test both on your own repository before choosing.
How many benchmarks do Mercury and Qwen3 32B share?
9 benchmarks have published results for both models. Mercury has 9 scored results on Noometry and Qwen3 32B has 26.