Qwen-Plus vs Qwen2.5 VL 72B Instruct
Qwen-Plus costs 1.3x less per output token than Qwen2.5 VL 72B Instruct ($0.78 vs $1.00 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.78
- Coding
- No data
- Overall
- No data
- Output $/M
- $1.00
Qwen-Plus 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 Qwen-Plus for output tokens 1.3x cheaper ($0.78 vs $1.00 per million) and a larger context window (1M against 128K tokens).
No benchmark has tested both yet. Qwen-Plus has results on LMArena Text: coding, LMArena Text: software and IT and GPQA Diamond (Epoch AI run); 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
Long documents
Listed context window
Qwen-Plus
Qwen-Plus takes 1M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen-Plus
Qwen-Plus $0.0006, Qwen2.5 VL 72B Instruct $0.0013 per turn.
List prices
At a glance
- Coding index
- Qwen-Plus 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
- Qwen-Plus $0.78 against Qwen2.5 VL 72B Instruct $1.00 per million output tokens, 1.3x apart.
- Context window
- Qwen-Plus 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.
CodingDirectional onlySix of these boards feed the Vibe Coding Index2 boards measured
| Benchmark | Qwen-Plus | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| LMArena Text: coding | 1328 | Not measured | Only Qwen-Plus measured |
| LMArena Text: software and IT | 1343 | Not measured | Only Qwen-Plus measured |
| Neither model has a result on the other 37 boards here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Qwen-Plus | 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 index5 boards measured
| Benchmark | Qwen-Plus | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond (Epoch AI run) | 48.1% | Not measured | Only Qwen-Plus measured |
| LMArena Text: hard prompts | 1317 | Not measured | Only Qwen-Plus measured |
| LMArena Text: expert | 1328 | Not measured | Only Qwen-Plus measured |
| LMArena Text: hard prompts in English | 1333 | Not measured | Only Qwen-Plus measured |
| Kagi LLM Benchmark | Not measured | 36.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards measured
| Benchmark | Qwen-Plus | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| OTIS Mock AIME | 17.8% | Not measured | Only Qwen-Plus measured |
| MATH level 5 | 65.3% | Not measured | Only Qwen-Plus measured |
| LMArena Text: math | 1326 | Not measured | Only Qwen-Plus measured |
| LMArena Text: mathematical work | 1332 | Not measured | Only Qwen-Plus measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Qwen-Plus | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| GeoBench | Not measured | 62.0% | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: science | 1352 | Not measured | Only Qwen-Plus measured |
| LMArena Text: medicine and healthcare | 1350 | Not measured | Only Qwen-Plus measured |
| LMArena Text: legal and government | 1349 | Not measured | Only Qwen-Plus measured |
| LMArena Text: business and finance | 1303 | Not measured | Only Qwen-Plus measured |
| Neither model has a result on the other 13 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index17 boards measured
| Benchmark | Qwen-Plus | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| DTBench | 81.1% | Not measured | Only Qwen-Plus measured |
| LMCA | 24.0% | Not measured | Only Qwen-Plus measured |
| LMArena Text | 1326 | Not measured | Only Qwen-Plus measured |
| LMArena Text: instruction following | 1303 | Not measured | Only Qwen-Plus measured |
| LMArena Text: creative writing | 1292 | Not measured | Only Qwen-Plus measured |
| LMArena Vision | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Text: English | 1339 | Not measured | Only Qwen-Plus measured |
| LMArena Text: non-English | 1310 | Not measured | Only Qwen-Plus measured |
| LMArena Text: Chinese | 1347 | Not measured | Only Qwen-Plus measured |
| LMArena Text: Japanese | 1251 | Not measured | Only Qwen-Plus measured |
| LMArena Text: Russian | 1323 | Not measured | Only Qwen-Plus measured |
| LMArena Text: multi-turn | 1336 | Not measured | Only Qwen-Plus measured |
| LMArena Text: longer queries | 1324 | Not measured | Only Qwen-Plus measured |
| LMArena Text: writing and language | 1296 | Not measured | Only Qwen-Plus measured |
| LMArena Text: entertainment and media | 1270 | Not measured | Only Qwen-Plus 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 29 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
Qwen-Plus costs less
Repository review
50K input + 3K output tokens
Qwen-Plus costs less
Agent loop
200K input + 10K output tokens
Qwen-Plus 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 | Qwen-Plus | Qwen2.5 VL 72B Instruct |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | No public weights listed | Open weights |
| Released | February 1, 2025 | February 1, 2025 |
| Context window | 1M | 128K |
| Input $/Mtok | $0.26 | $0.80 |
| Output $/Mtok | $0.78 | $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 Qwen-Plus 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 Qwen-Plus for output tokens 1.3x cheaper ($0.78 vs $1.00 per million) and a larger context window (1M against 128K tokens).
Which is cheaper, Qwen-Plus or Qwen2.5 VL 72B Instruct?
Qwen-Plus costs $0.26 per million input tokens and $0.78 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, Qwen-Plus or Qwen2.5 VL 72B Instruct?
Qwen-Plus, with 1M tokens against 128K.
Has any benchmark tested both Qwen-Plus and Qwen2.5 VL 72B Instruct?
No benchmark has tested both yet. Qwen-Plus has results on LMArena Text: coding, LMArena Text: software and IT and GPQA Diamond (Epoch AI run); Qwen2.5 VL 72B Instruct on OSWorld, Kagi LLM Benchmark and GeoBench. Compare them on price and context instead. Data as of October 21, 2026.