Model comparison
Mercury 2 vs Qwen2-72B
Mercury 2 is the stronger model overall, scoring 39.1 to 30.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Mercury 2 scores higher in 7 categories and Qwen2-72B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 21.2.
- The biggest single-benchmark swing is WeirdML: 43.2% for Mercury 2 and 11.3% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Qwen2-72B | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 39.1 | 30.0 |
| Released | 2026-02-20 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 50K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 17 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Mercury 2: 33.5 (#255), Qwen2-72B: 29.1 (#310)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| WeirdML | 43.2% | 11.3% |
| LMArena Coding | 1391 | 1196 |
| LMArena WebDev | 1171 | — |
| SciCode | 38.7% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Mercury 2: 23.8 (#170), Qwen2-72B: 23.2 (#181)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1191 |
| CritPt | 0.8% | — |
| Epoch Capabilities Index | — | 125.28 |
Math Not comparable
Mercury 2: —, Qwen2-72B: 30.2 (#236)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Mercury 2 leads
Mercury 2: 36.2 (#172), Qwen2-72B: 21.2 (#275)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1358 | 1171 |
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 12.3% | — |
| MMLU | — | 82.4% |
Multilingual Mercury 2 leads
Mercury 2: 46.6 (#157), Qwen2-72B: 35.9 (#244)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1331 | 1176 |
| LMArena Chinese | 1417 | 1240 |
| LMArena Russian | 1304 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |
Instruction Following Mercury 2 leads
Mercury 2: 70.2 (#165), Qwen2-72B: 61.7 (#241)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1181 |
Long Context Mercury 2 leads
Mercury 2: 40.5 (#154), Qwen2-72B: 36.1 (#235)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1330 | 1192 |
Writing & Preference Mercury 2 leads
Mercury 2: 53.8 (#155), Qwen2-72B: 40.8 (#241)
| Benchmark | Mercury 2 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1355 | 1203 |
| LMArena Creative Writing | 1289 | 1181 |
| LMArena Multi-Turn | 1358 | 1196 |
Frequently asked questions
Is Mercury 2 better than Qwen2-72B?
Mercury 2 is the stronger model overall, scoring 39.1 to 30.0 on the Noometry Index.
Is Mercury 2 or Qwen2-72B better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 29.1 in the Noometry coding category.
How many benchmarks do Mercury 2 and Qwen2-72B share?
12 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen2-72B has 26.