deepseek-chat: benchmark scores, price and ranking
deepseek-chat from DeepSeek ranks #516 of 743 LLMs on the LLMs Tiger aggregate benchmark score (46.5), based on 5 benchmark results captured up to 2026-10-13.
- Organisation
- DeepSeek
- Type
- Frontier model
- Open weights
- No
- Released
- 2025-12-01 (source: epoch)
- Context window
- 131,072 tokens
- Cheapest API price
- $0.280 in / $0.420 out per million tokens (via deepseek, observed 2026-10-13T20:47Z)
- Aggregate rank
- #516 of 743 (score 46.5)
Relative to other models, deepseek-chat is strongest on GPQA Diamond (#142 of 275) and weakest on LMCA (#87 of 108).
Across the 5 benchmarks where at least ten models are scored, deepseek-chat is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $0.280 per million tokens, is lower than that of 62% of the 427 models with a listed price.
deepseek-chat benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 71.2% | #142 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 48.9% | #108 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 62.7% | #90 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 1.0% | #92 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 15.2% | #87 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
About deepseek-chat
deepseek-chat is a frontier model from DeepSeek. It was released on 2025-12-01, according to Epoch AI. It accepts up to 131,072 tokens of input at once. The cheapest API listing we track charges $0.280 per million input tokens and $0.420 per million output tokens, through deepseek. We hold 5 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where deepseek-chat stands
On our aggregate score, deepseek-chat is #516 of 743 ranked models, in the lower half. Its score is 46.5; the scale is centred on 50, so it sits 3.5 points below the typical model. That beats 31% of the ranked field. Among the 33 ranked DeepSeek models it is #26. The next one up is DeepSeek-R1-Distill-Qwen-14B at 47.0. The next one down is DeepSeek Chat V2.5 at 46.3.
deepseek-chat, benchmark by benchmark
deepseek-chat lands below the middle on GPQA Diamond: 71.2%, #142 of 275, with 51% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is claude-haiku-4-5-20251001_32K at 71.2%. It covers expert-level science questions. The board median is 71.7%, so deepseek-chat is 0.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
deepseek-chat lands below the middle on OTIS Mock AIME: 48.9%, #108 of 189, with 57% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is DeepSeek-R1-Distill-Qwen-14B at 50.6%. It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so deepseek-chat is 8.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
deepseek-chat lands below the middle on DTBench: 62.7%, #90 of 146, with 61% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is gemini-2.5-flash-lite-preview-06-17 (Default thinking length) at 62.8%. It covers dynamic tool-use benchmark. The board median is 68.8%, so deepseek-chat is 6.1 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
deepseek-chat lands below the middle on Chess Puzzles: 1.0%, #92 of 122, with 75% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is qwen3-30b-a3b-instruct-2507 at 2.0%. It covers chess tactics puzzles. The board median is 12.5%, so deepseek-chat is 11.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMCA is a weak spot. deepseek-chat scores 15.2%, #87 of 108, behind 80% of the models measured. The leader, Claude Opus 5.5 (max), reaches 68.2%. It covers language-model capability assessment. The board median is 29.2%, so deepseek-chat is 14.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 46% of the field on average across 2 benchmarks. Its best board here is GPQA Diamond (#142 of 275) and its weakest is OTIS Mock AIME (#108 of 189). General knowledge and chat: weak, ahead of 22% of the field on average across 2 benchmarks. Its best board here is Chess Puzzles (#92 of 122) and its weakest is LMCA (#87 of 108).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so deepseek-chat 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 Gemini 2.5 Flash (Preview) (Thinking 24K) ($0.300) and Command A+ ($0.300).
Release history
The DeepSeek model released before it was DeepSeek-V3.1-Terminus on 2025-09-22, which scores 47.4. The next one was DeepSeek-V3.2 on 2025-12-01, at 47.7.
Reading these numbers
The 5 scores on this page come from 1 source: Epoch AI Benchmarking Hub (5). No official leaderboard supplied any of them, so treat them as third-party measurements. With 5 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #513 Mistral Small 4 (46.5)
- #514 Qwen2-VL-7B-Instruct (46.5)
- #515 Gemma 2 9B (46.5)
- #517 Qwen2.5-7B (46.5)
- #518 qwen3-1.7b (46.5)
- #519 Qwen3.5 Flash (46.4)
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