Mercury 3 vs Qwen2.5 VL 72B Instruct
Mercury 3 costs 2.9x less per output token than Qwen2.5 VL 72B Instruct ($0.35 vs $1.00 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.35
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.00
Mercury 3 or Qwen2.5 VL 72B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mercury 3 for output tokens 2.9x cheaper ($0.35 vs $1.00 per million) and a larger context window (1M against 128K tokens).
No benchmark has tested both yet. Mercury 3 has results on Design Arena: websites, Design Arena: UI components and Design Arena: game dev; Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Web design
Design Arena: websites
No call
Only Mercury 3 has a Design Arena: websites result, 1229.
Directional only
Long documents
Listed context window
Mercury 3
Mercury 3 takes 1M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 3
Mercury 3 $0.0003, Qwen2.5 VL 72B Instruct $0.0013 per turn.
List prices
At a glance
- Coding index
- Mercury 3 not benchmarked, Qwen2.5 VL 72B Instruct not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Mercury 3 $0.35 against Qwen2.5 VL 72B Instruct $1.00 per million output tokens, 2.9x apart.
- Context window
- Mercury 3 takes 1M tokens, Qwen2.5 VL 72B Instruct 128K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Mercury 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| OSWorld | Not measured | 5.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Mercury 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| Kagi LLM Benchmark | Not measured | 36.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 21 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Mercury 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| GeoBench | Not measured | 62.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 17 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Mercury 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1229 | Not measured | Only Mercury 3 measured |
| Design Arena: UI components | 1253 | Not measured | Only Mercury 3 measured |
| Design Arena: game dev | 1224 | Not measured | Only Mercury 3 measured |
| Design Arena: data viz | 1205 | Not measured | Only Mercury 3 measured |
| Design Arena: all code categories | 1232 | Not measured | Only Mercury 3 measured |
| Neither model has a result on the other 4 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | Mercury 3 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| LMArena Vision | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: English | Not measured | 1115 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: Chinese | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 43 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Mercury 3 costs less
Repository review
50K input + 3K output tokens
Mercury 3 costs less
Agent loop
200K input + 10K output tokens
Mercury 3 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Inception Mercury 3 | Qwen2.5 VL 72B Instruct |
|---|---|---|
| Maker | Inception | Qwen |
| Weights | No public weights listed | Open weights |
| Released | October 16, 2026 | February 1, 2025 |
| Context window | 1M | 128K |
| Input $/Mtok | $0.10 | $0.80 |
| Output $/Mtok | $0.35 | $1.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mercury 3 better than Qwen2.5 VL 72B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mercury 3 for output tokens 2.9x cheaper ($0.35 vs $1.00 per million) and a larger context window (1M against 128K tokens).
Which is cheaper, Mercury 3 or Qwen2.5 VL 72B Instruct?
Mercury 3 costs $0.10 per million input tokens and $0.35 per million output tokens; Qwen2.5 VL 72B Instruct costs $0.80 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Mercury 3 or Qwen2.5 VL 72B Instruct?
Mercury 3, with 1M tokens against 128K.
Has any benchmark tested both Mercury 3 and Qwen2.5 VL 72B Instruct?
No benchmark has tested both yet. Mercury 3 has results on Design Arena: websites, Design Arena: UI components and Design Arena: game dev; Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead. Data as of October 22, 2026.