Model comparison
Qwen2.5-VL 72B Instruct vs Qwen3 8B
Qwen3 8B is the stronger model overall, scoring 33.7 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in agentic & tool use, where Qwen3 8B leads 30.2 to 18.6.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
Side by side
| Qwen2.5-VL 72B Instruct | Qwen3 8B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.9 | 33.7 |
| Released | 2024-09 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $2.80 | $0.18 |
| Output $ / M tokens | $8.40 | $0.70 |
| Results tracked | 6 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen2.5-VL 72B Instruct: —, Qwen3 8B: 34.0 (#248)
| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |
Agentic & Tool Use Qwen3 8B leads
Qwen2.5-VL 72B Instruct: 18.6 (#144), Qwen3 8B: 30.2 (#78)
| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
| OSWorld | 5% | — |
Reasoning Qwen2.5-VL 72B Instruct leads
Qwen2.5-VL 72B Instruct: 20.7 (#233), Qwen3 8B: 16.6 (#303)
| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 8B |
|---|---|---|
| Kagi LLM Benchmark | 36% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |
Math Not comparable
Qwen2.5-VL 72B Instruct: —, Qwen3 8B: 34.9 (#191)
| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
Knowledge Not comparable
Qwen2.5-VL 72B Instruct: —, Qwen3 8B: 36.1 (#173)
| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 8B |
|---|---|---|
| GPQA Diamond | — | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
Multimodal Not comparable
Qwen2.5-VL 72B Instruct: 33.5 (#97), Qwen3 8B: —
| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 8B |
|---|---|---|
| LMArena Vision | 1107 | — |
| Video-MME | 73.5% | — |
| GeoBench | 62% | — |
| SpatialViz-Bench | 33.3% | — |
Long Context Not comparable
Qwen2.5-VL 72B Instruct: —, Qwen3 8B: 37.9 (#210)
| Benchmark | Qwen2.5-VL 72B Instruct | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Frequently asked questions
Is Qwen2.5-VL 72B Instruct better than Qwen3 8B?
Qwen3 8B is the stronger model overall, scoring 33.7 to 29.9 on the Noometry Index.
Which is cheaper, Qwen2.5-VL 72B Instruct or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Qwen2.5-VL 72B Instruct and Qwen3 8B share?
0 benchmarks have published results for both models. Qwen2.5-VL 72B Instruct has 6 scored results on Noometry and Qwen3 8B has 11.