Model comparison
DeepSeek-V3.1-Terminus vs Qwen2.5 7B Instruct
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 1.6× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 5 categories and Qwen2.5 7B Instruct in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 35.7 to 11.8.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 47.7% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 131K.
Side by side
| DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.6 | 28.6 |
| Released | 2025-09-22 | 2024-09 |
| Weights | Open | Open |
| Context window | 164K | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.30 | $0.17 |
| Output $ / M tokens | $1 | $0.70 |
| Results tracked | 16 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| SciCode | 40.6% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1426 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 81.3% | 47.7% |
| LMCA | 28.6% | 6.4% |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1427 | — |
| Epoch Capabilities Index | — | 118.44 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1402 | — |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| MMLU | — | 72.9% |
Multilingual Not comparable
DeepSeek-V3.1-Terminus: 52.3 (#87), Qwen2.5 7B Instruct: —
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1407 | — |
| LMArena Russian | 1434 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1406 | — |
Long Context Not comparable
DeepSeek-V3.1-Terminus: 43.5 (#88), Qwen2.5 7B Instruct: —
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1426 | — |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1404 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1411 | — |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen2.5 7B Instruct?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 1.6× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus 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-V3.1-Terminus lists at $0.30 and $1.
Is DeepSeek-V3.1-Terminus or Qwen2.5 7B Instruct better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 131K.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen2.5 7B Instruct share?
2 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen2.5 7B Instruct has 15.