DeepSeek-V3.1: benchmark scores, price and ranking
DeepSeek-V3.1 from DeepSeek ranks #387 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.0), based on 4 benchmark results captured up to 2026-10-13.
- Organisation
- DeepSeek
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-08-21 (source: epoch)
- Cheapest API price
- $0.250 in / $0.950 out per million tokens (via deepinfra, observed 2026-10-13T20:47Z)
- Aggregate rank
- #387 of 743 (score 48.0)
Relative to other models, DeepSeek-V3.1 is strongest on Epoch ECI (#52 of 204) and weakest on Fiction.liveBench (#31 of 47).
Across the 4 benchmarks where at least ten models are scored, DeepSeek-V3.1 is in the top 10% on 0 and in the top half on 1.
Its cheapest listed input price, $0.250 per million tokens, is lower than that of 64% of the 427 models with a listed price.
DeepSeek-V3.1 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 140 | #52 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 40.0% | #35 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 37.5% | #71 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 52.8% | #31 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
About DeepSeek-V3.1
DeepSeek-V3.1 is an open-weight model that can run on your own hardware from DeepSeek. It was released on 2025-08-21, according to Epoch AI. The cheapest API listing we track charges $0.250 per million input tokens and $0.950 per million output tokens, through deepinfra. We hold 4 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where DeepSeek-V3.1 stands
On our aggregate score, DeepSeek-V3.1 is #387 of 743 ranked models, around the middle of the table. Its score is 48.0; the scale is centred on 50, so it sits 2.0 points below the typical model. That beats 48% of the ranked field. Among the 33 ranked DeepSeek models it is #17. The next one up is DeepSeek-R1 (May 2025) at 48.2. The next one down is DeepSeek-R1-Distill-Llama-70B at 48.0.
DeepSeek-V3.1, benchmark by benchmark
Epoch ECI puts DeepSeek-V3.1 at 140, #52 of 204. That beats 75% of the models tested, but 16 points short of Qwen 3.8 Max (156). The results either side are Gemini 2.5 Flash (Apr 2025) (140) and Qwen3-30B-A3B-Thinking (Jul 2025) (140). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so DeepSeek-V3.1 is 13 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
DeepSeek-V3.1 lands below the middle on SimpleBench: 40.0%, #35 of 61, with 56% of the field scoring higher. Claude Fable 5 (max) leads at 81.9%; the closest result above is o1 (high) at 40.1%. It covers trick questions that test common sense. The board median is 41.4%, so DeepSeek-V3.1 is 1.4 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
DeepSeek-V3.1 lands below the middle on WeirdML: 37.5%, #71 of 109, with 64% of the field scoring higher. GPT-6 Astra (max) leads at 93.3%; the closest result above is GPT-4.1 mini at 37.6%. It covers unusual machine-learning tasks. The board median is 41.2%, so DeepSeek-V3.1 is 3.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
DeepSeek-V3.1 lands below the middle on Fiction.liveBench: 52.8%, #31 of 47, with 64% of the field scoring higher. grok-4-0709 leads at 94.4%; the closest result above is parasail-qwen3-235b-a22b-instruct-2507 at 52.9%. It covers long-context story comprehension (16k). The board median is 61.1%, so DeepSeek-V3.1 is 8.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
General knowledge and chat: uneven, ahead of 48% of the field on average across 3 benchmarks. Its best board here is Epoch ECI (#52 of 204) and its weakest is Fiction.liveBench (#31 of 47).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so DeepSeek-V3.1 costs less than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on DeepSeek-V3.2 (Thinking; Fireworks) ($0.259) and DeepSeek-V3.2 ($0.259).
Release history
The DeepSeek model released before it was DeepSeek-R1 (May 2025) on 2025-05-28, which scores 48.2. The next one was DeepSeek-V3.1-Terminus on 2025-09-22, at 47.4.
Reading these numbers
The 4 scores on this page come from 1 source: Epoch AI Benchmarking Hub (4). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 1 other reasoning-effort setting of this model, which redirect here. This page shows the highest. With 4 results the aggregate rank can move a lot when one new score arrives.
DeepSeek-V3.1 is also listed at 1 other reasoning-effort setting; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #384 ERNIE-4.5-21B-A3B-Base-PT (48.1)
- #385 Llama-3.2-11B-Vision-Instruct (48.0)
- #386 Gemini 3.5 Flash-Lite (High) (48.0)
- #388 DeepSeek-R1-Distill-Llama-70B (48.0)
- #389 DeepSeek-R1 (48.0)
- #390 qwen3-coder-plus (48.0)
More from DeepSeek
- DeepSeek V4 Pro 0813 (max) (#23, 54.3)
- DeepSeek V4 Flash 0731 (max) (#42, 53.1)
- DeepSeek-V3.2-Exp (high) (#67, 52.4)
- deepseek-v4.1-flash-max (#75, 52.2)
- DeepSeek-V2.5-1210 (#101, 51.7)
- DeepSeek v4 Pro (max) (#108, 51.6)
Compare it on the live leaderboard → · How the aggregate score works