Model comparison
Mercury 2 vs Qwen2.5-VL 72B Instruct
Mercury 2 is the stronger model overall, scoring 38.8 to 29.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Mercury 2 leads 23.0 to 20.0.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Qwen2.5-VL 72B Instruct accepts more context: 131K tokens versus 128K.
- Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Qwen2.5-VL 72B Instruct | |
|---|---|---|
| Provider | Inception | Alibaba (Qwen) |
| Noometry Index | 38.8 | 29.4 |
| Released | 2026-02-20 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 128K | 131K |
| Max output | 50K | 8K |
| Input $ / M tokens | $0.25 | $2.80 |
| Output $ / M tokens | $0.75 | $8.40 |
| 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), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| LMArena Coding | 1391 | — |
| ALE-Bench | 785.58 | — |
Agentic & Tool Use Not comparable
Mercury 2: —, Qwen2.5-VL 72B Instruct: 18.4 (#136)
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| OSWorld | — | 5% |
Reasoning Mercury 2 leads
Mercury 2: 23.0 (#170), Qwen2.5-VL 72B Instruct: 20.0 (#228)
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 36% |
| CritPt | 0.8% | — |
| LMArena Hard Prompts | 1362 | — |
Knowledge Not comparable
Mercury 2: 35.6 (#170), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | — |
| LMArena Expert | 1358 | — |
Multimodal Not comparable
Mercury 2: —, Qwen2.5-VL 72B Instruct: 32.9 (#92)
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Vision | — | 1107 |
| Video-MME | — | 73.5% |
| GeoBench | — | 62% |
| SpatialViz-Bench | — | 33.3% |
Multilingual Not comparable
Mercury 2: 46.8 (#153), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Non-English | 1331 | — |
| LMArena Chinese | 1416 | — |
| LMArena Russian | 1303 | — |
Instruction Following Not comparable
Mercury 2: 70.4 (#161), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1328 | — |
Long Context Not comparable
Mercury 2: 40.4 (#149), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1329 | — |
Writing & Preference Not comparable
Mercury 2: 54.0 (#151), Qwen2.5-VL 72B Instruct: —
| Benchmark | Mercury 2 | Qwen2.5-VL 72B Instruct |
|---|---|---|
| LMArena Text | 1355 | — |
| LMArena Creative Writing | 1289 | — |
| LMArena Multi-Turn | 1358 | — |
Frequently asked questions
Is Mercury 2 better than Qwen2.5-VL 72B Instruct?
Mercury 2 is the stronger model overall, scoring 38.8 to 29.4 on the Noometry Index.
Which is cheaper, Mercury 2 or Qwen2.5-VL 72B Instruct?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Qwen2.5-VL 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Mercury 2 and Qwen2.5-VL 72B Instruct share?
0 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.