Model comparison
Mercury 2 vs Qwen3-4B
Mercury 2 is the stronger model overall, scoring 38.8 to 31.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Mercury 2 scores higher in 2 categories and Qwen3-4B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury 2 leads 23.0 to 18.5.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12.3% for Mercury 2 and 5.7% for Qwen3-4B.
- Qwen3-4B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Qwen3-4B | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 31.5 |
| Released | 2026-02-20 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 50K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 17 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mercury 2: 33.2 (#250), Qwen3-4B: —
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| LMArena Coding | 1391 | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Qwen3-4B: 27.3 (#94)
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Mercury 2 leads
Mercury 2: 23.0 (#170), Qwen3-4B: 18.5 (#264)
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| CritPt | 0.8% | — |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1362 | — |
Math Not comparable
Mercury 2: —, Qwen3-4B: 28.5 (#228)
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
Knowledge Mercury 2 leads
Mercury 2: 35.6 (#170), Qwen3-4B: 33.0 (#198)
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | 5.7% |
| GPQA Diamond | — | 52.3% |
| LMArena Expert | 1358 | — |
Multilingual Not comparable
Mercury 2: 46.8 (#153), Qwen3-4B: —
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1331 | — |
| LMArena Chinese | 1416 | — |
| LMArena Russian | 1303 | — |
Instruction Following Not comparable
Mercury 2: 70.4 (#161), Qwen3-4B: —
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1328 | — |
Long Context Not comparable
Mercury 2: 40.4 (#149), Qwen3-4B: —
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1329 | — |
Writing & Preference Not comparable
Mercury 2: 54.0 (#151), Qwen3-4B: —
| Benchmark | Mercury 2 | Qwen3-4B |
|---|---|---|
| LMArena Text | 1355 | — |
| LMArena Creative Writing | 1289 | — |
| LMArena Multi-Turn | 1358 | — |
Frequently asked questions
Is Mercury 2 better than Qwen3-4B?
Mercury 2 is the stronger model overall, scoring 38.8 to 31.5 on the Noometry Index.
How many benchmarks do Mercury 2 and Qwen3-4B share?
1 benchmark has published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen3-4B has 6.