← All benchmarks
DeepSeek V3.1 Terminus (Non-reasoning)
DeepSeek · Released 2025-09-22 · Independent benchmark scores from Artificial Analysis
Intelligence Index
21.4
Output speed
0.0
tokens/sec
Blended price
$0.45
per 1M tokens
Time to first token
0.00s
Model metadata
| Model ID | dfb9292d-bc7c-4425-a260-4256217e709f |
|---|---|
| Slug | deepseek-v3-1-terminus |
| Release date | 2025-09-22 |
| Provider | DeepSeek |
| Provider slug | deepseek |
| Output speed | 0.0 tok/s |
| Time to first token | 0.00s |
| Time to first answer | 0.00s |
| Blended price ($/1M) | $0.45 |
| Input price ($/1M) | $0.27 |
| Output price ($/1M) | $1.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | 53.7% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 21.40 |
| artificial analysis math index | 53.70 |
| gpqa | 75.1% |
| hle | 8.4% |
| ifbench | 41.2% |
| lcr | 43.3% |
| livecodebench | 52.9% |
| math 500 | — |
| mmlu pro | 83.6% |
| scicode | 32.1% |
| tau banking | — |
| tau2 | 37.1% |
| terminalbench hard | 31.8% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/deepseek-v3-1-terminus
Benchmark data from Artificial Analysis.