Model comparison
Mercury 2 vs Qwen3-Coder 480B-A35B Instruct
Mercury 2 is the stronger model overall, scoring 39.1 to 38.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Qwen3-Coder 480B-A35B Instruct in 7 categories; 6 gaps are clear of the uncertainty.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 128K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 39.1 | 38.1 |
| Released | 2026-02-20 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 50K | 66K |
| Input $ / M tokens | $0.25 | $1.50 |
| Output $ / M tokens | $0.75 | $7.50 |
| Results tracked | 17 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
Mercury 2: 33.5 (#255), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1171 | 1275 |
| WeirdML | 43.2% | 41.2% |
| LMArena Coding | 1391 | 1412 |
| ALE-Bench | 785.58 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| SciCode | 38.7% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
Mercury 2: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Mercury 2: 23.8 (#170), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | — | 1365 |
Knowledge Too close to call
Mercury 2: 36.2 (#172), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1358 | 1338 |
| Vectara Hallucination Rate | 12.3% | — |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Mercury 2: 46.6 (#157), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1331 | 1346 |
| LMArena Chinese | 1417 | 1357 |
| LMArena Russian | 1304 | 1366 |
| LMArena French | — | 1398 |
| LMArena German | — | 1325 |
| LMArena Japanese | — | 1310 |
| LMArena Korean | — | 1305 |
| LMArena Spanish | — | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Mercury 2: 70.2 (#165), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1329 | 1355 |
Long Context Qwen3-Coder 480B-A35B Instruct leads
Mercury 2: 40.5 (#154), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1330 | 1378 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Mercury 2: 53.8 (#155), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Mercury 2 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1355 | 1357 |
| LMArena Creative Writing | 1289 | 1333 |
| LMArena Multi-Turn | 1358 | 1365 |
Frequently asked questions
Is Mercury 2 better than Qwen3-Coder 480B-A35B Instruct?
Mercury 2 is the stronger model overall, scoring 39.1 to 38.1 on the Noometry Index.
Which is cheaper, Mercury 2 or Qwen3-Coder 480B-A35B Instruct?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Mercury 2 or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 128K.
How many benchmarks do Mercury 2 and Qwen3-Coder 480B-A35B Instruct share?
14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.