Model comparison
Mercury 2 vs Qwen1.5 4b Chat
Mercury 2 is the stronger model overall, scoring 38.8 to 28.3 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Mercury 2 scores higher in 7 categories and Qwen1.5 4b Chat in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 54.0 to 23.9.
- Qwen1.5 4b Chat has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 28.3 |
| Released | 2026-02-20 | — |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 50K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 17 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Mercury 2: 33.2 (#250), Qwen1.5 4b Chat: 28.6 (#305)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1391 | 999 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |
Reasoning Mercury 2 leads
Mercury 2: 23.0 (#170), Qwen1.5 4b Chat: 17.7 (#277)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1362 | 976 |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, Qwen1.5 4b Chat: 27.9 (#233)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | — | 1026 |
Knowledge Mercury 2 leads
Mercury 2: 35.6 (#170), Qwen1.5 4b Chat: 26.2 (#252)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1358 | 980 |
| Vectara Hallucination Rate | 12.3% | — |
Multilingual Mercury 2 leads
Mercury 2: 46.8 (#153), Qwen1.5 4b Chat: 24.2 (#285)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1331 | 979 |
| LMArena Chinese | 1416 | 1024 |
| LMArena Russian | 1303 | 952 |
| LMArena German | — | 902 |
Instruction Following Mercury 2 leads
Mercury 2: 70.4 (#161), Qwen1.5 4b Chat: 49.3 (#295)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1328 | 979 |
Long Context Mercury 2 leads
Mercury 2: 40.4 (#149), Qwen1.5 4b Chat: 30.1 (#285)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1329 | 988 |
Writing & Preference Mercury 2 leads
Mercury 2: 54.0 (#151), Qwen1.5 4b Chat: 23.9 (#304)
| Benchmark | Mercury 2 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1355 | 997 |
| LMArena Creative Writing | 1289 | 969 |
| LMArena Multi-Turn | 1358 | 977 |
Frequently asked questions
Is Mercury 2 better than Qwen1.5 4b Chat?
Mercury 2 is the stronger model overall, scoring 38.8 to 28.3 on the Noometry Index.
Is Mercury 2 or Qwen1.5 4b Chat better for coding?
Mercury 2 scores higher on coding benchmarks: 33.2 versus 28.6 in the Noometry coding category.
How many benchmarks do Mercury 2 and Qwen1.5 4b Chat share?
11 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen1.5 4b Chat has 13.