Model comparison
Mercury 2 vs Qwen2.5 72B Instruct
Mercury 2 is the stronger model overall, scoring 38.8 to 31.5 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 Qwen2.5 72B Instruct in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 35.6 to 26.9.
- The biggest single-benchmark swing is WeirdML: 43.2% for Mercury 2 and 16% for Qwen2.5 72B Instruct.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 31.5 |
| Released | 2026-02-20 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 50K | 8K |
| Input $ / M tokens | $0.25 | $1.40 |
| Output $ / M tokens | $0.75 | $5.60 |
| Results tracked | 17 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury 2: 33.2 (#250), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 43.2% | 16% |
| LMArena Coding | 1391 | 1293 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Mercury 2 leads
Mercury 2: 23.0 (#170), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1271 |
| CritPt | 0.8% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Not comparable
Mercury 2: —, Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge Mercury 2 leads
Mercury 2: 35.6 (#170), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1358 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 12.3% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Mercury 2 leads
Mercury 2: 46.8 (#153), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1331 | 1252 |
| LMArena Chinese | 1416 | 1272 |
| LMArena Russian | 1303 | 1264 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1255 |
Instruction Following Mercury 2 leads
Mercury 2: 70.4 (#161), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1328 | 1254 |
| IFEval | — | 80.6% |
Long Context Mercury 2 leads
Mercury 2: 40.4 (#149), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1329 | 1282 |
Writing & Preference Mercury 2 leads
Mercury 2: 54.0 (#151), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Mercury 2 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1355 | 1269 |
| LMArena Creative Writing | 1289 | 1221 |
| LMArena Multi-Turn | 1358 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Mercury 2 better than Qwen2.5 72B Instruct?
Mercury 2 is the stronger model overall, scoring 38.8 to 31.5 on the Noometry Index.
Which is cheaper, Mercury 2 or Qwen2.5 72B Instruct?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Mercury 2 or Qwen2.5 72B Instruct better for coding?
They score almost the same on coding (33.2 vs 32.8); test both on your own repository before choosing.
Which has the bigger context window?
Qwen2.5 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Mercury 2 and Qwen2.5 72B Instruct share?
12 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen2.5 72B Instruct has 43.