Model comparison
DeepSeek V4 Pro vs Qwen2.5 7B Instruct
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 3.2× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 7 categories and Qwen2.5 7B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.8 to 12.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.6% for DeepSeek V4 Pro and 2.5% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.66 / $1.98 for DeepSeek V4 Pro.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 131K.
Side by side
| DeepSeek V4 Pro | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 54.3 | 29.0 |
| Released | 2026-04-24 | 2024-09 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 393K | 8K |
| Input $ / M tokens | $0.66 | $0.17 |
| Output $ / M tokens | $1.98 | $0.70 |
| Results tracked | 48 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1470 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use DeepSeek V4 Pro leads
DeepSeek V4 Pro: 32.8 (#58), Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| APEX-Agents | 47.3% | — |
| BALROG | — | 7.8% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 47% | 0% |
| DTBench | 93.9% | 47.7% |
| LMCA | 45.5% | 6.4% |
| Epoch Capabilities Index | 155.31 | 118.51 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.6% | 2.5% |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1455 | — |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 91.7% | 35.5% |
| SimpleQA Verified | 52.9% | — |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 8.6% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1464 | — |
| MMLU | — | 72.9% |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), Qwen2.5 7B Instruct: —
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Qwen2.5 7B Instruct: —
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| WildBench | — | 73.1% |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Qwen2.5 7B Instruct?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 3.2× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Pro or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; DeepSeek V4 Pro lists at $0.66 and $1.98.
Is DeepSeek V4 Pro or Qwen2.5 7B Instruct better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Pro does, with 1M tokens against 131K.
How many benchmarks do DeepSeek V4 Pro and Qwen2.5 7B Instruct share?
6 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen2.5 7B Instruct has 15.