DeepSeek-R1-Distill-Qwen-14B: benchmark scores, price and ranking
DeepSeek-R1-Distill-Qwen-14B from DeepSeek ranks #469 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.0), based on 4 benchmark results captured up to 2026-10-14.
- Organisation
- DeepSeek
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2025-01-20 (source: epoch)
- Cheapest API price
- $0.070 in / $0.070 out per million tokens (via nscale, observed 2026-10-14T22:47Z)
- Aggregate rank
- #469 of 743 (score 47.0)
Relative to other models, DeepSeek-R1-Distill-Qwen-14B is strongest on Epoch ECI (#69 of 204) and weakest on GPQA Diamond (#212 of 277).
Across the 4 benchmarks where at least ten models are scored, DeepSeek-R1-Distill-Qwen-14B is in the top 10% on 0 and in the top half on 1.
Its cheapest listed input price, $0.070 per million tokens, is lower than that of 88% of the 427 models with a listed price.
DeepSeek-R1-Distill-Qwen-14B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 135 | #69 of 204 | Epoch AI Benchmarking Hub | 2026-10-14 |
| OTIS Mock AIME | 50.6% | #108 of 190 | Epoch AI Benchmarking Hub | 2026-10-14 |
| Chess Puzzles | 1.0% | #93 of 122 | Epoch AI Benchmarking Hub | 2026-10-14 |
| GPQA Diamond | 44.7% | #212 of 277 | Epoch AI Benchmarking Hub | 2026-10-14 |
About DeepSeek-R1-Distill-Qwen-14B
DeepSeek-R1-Distill-Qwen-14B is an open-weight model that can run on your own hardware from DeepSeek. It was released on 2025-01-20, according to Epoch AI. The cheapest API listing we track charges $0.070 per million input tokens and $0.070 per million output tokens, through nscale. We hold 4 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where DeepSeek-R1-Distill-Qwen-14B stands
On our aggregate score, DeepSeek-R1-Distill-Qwen-14B is #469 of 743 ranked models, in the lower half. Its score is 47.0; the scale is centred on 50, so it sits 3.0 points below the typical model. That beats 37% of the ranked field. Among the 33 ranked DeepSeek models it is #25. The next one up is DeepSeek-V3.1-Terminus at 47.0. The next one down is deepseek-chat at 46.4.
DeepSeek-R1-Distill-Qwen-14B, benchmark by benchmark
Epoch ECI puts DeepSeek-R1-Distill-Qwen-14B at 135, #69 of 204. That beats 66% of the models tested, but 21 points short of Qwen 3.8 Max (156). The results either side are DeepSeek-V3 (Mar 2025) (136) and Gemini 2.0 Flash Thinking (Jan 2025) (135). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so DeepSeek-R1-Distill-Qwen-14B is 8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
DeepSeek-R1-Distill-Qwen-14B lands below the middle on OTIS Mock AIME: 50.6%, #108 of 190, with 56% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is gpt-oss-20b (high) at 50.8%. It covers competition maths (AIME 2024-25 style). The board median is 58.1%, so DeepSeek-R1-Distill-Qwen-14B is 7.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
DeepSeek-R1-Distill-Qwen-14B lands below the middle on Chess Puzzles: 1.0%, #93 of 122, with 75% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is deepseek-chat at 1.0%. It covers chess tactics puzzles. The board median is 12.5%, so DeepSeek-R1-Distill-Qwen-14B is 11.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
DeepSeek-R1-Distill-Qwen-14B lands below the middle on GPQA Diamond: 44.7%, #212 of 277, with 76% of the field scoring higher. gemini-4-argon-high leads at 96.4%; the closest result above is mistral-small-2501 at 45.3%. It covers expert-level science questions. The board median is 72.2%, so DeepSeek-R1-Distill-Qwen-14B is 27.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 33% of the field on average across 2 benchmarks. Its best board here is OTIS Mock AIME (#108 of 190) and its weakest is GPQA Diamond (#212 of 277). General knowledge and chat: uneven, ahead of 45% of the field on average across 2 benchmarks. Its best board here is Epoch ECI (#69 of 204) and its weakest is Chess Puzzles (#93 of 122).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so DeepSeek-R1-Distill-Qwen-14B costs less than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4.1 Flash (high) ($0.010, 49.7), Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on gemini-2.0-flash-lite ($0.075) and Gemma 4 26B A4B ($0.076).
Release history
The DeepSeek model released before it was DeepSeek-R1-Distill-Qwen-1.5B on 2025-01-20, which scores 44.5. The next one was DeepSeek-R1-Distill-Qwen-32B on 2025-01-20, at 47.9.
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. With 4 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #466 qwen3-30b-a3b-thinking-2507 (47.0)
- #467 Reflection-70B (47.0)
- #468 DeepSeek-V3.1-Terminus (47.0)
- #470 Magistral Medium 1.2 (46.9)
- #471 magistral-small-2506 (46.9)
- #472 Mistral-Small-Instruct-2409 (46.9)
More from DeepSeek
- DeepSeek V4 Pro 0813 (max) (#24, 54.2)
- DeepSeek V4 Flash 0731 (max) (#47, 53.0)
- DeepSeek-V3.2-Exp (high) (#67, 52.4)
- deepseek-v4.1-flash-max (#83, 52.1)
- DeepSeek-V2.5-1210 (#102, 51.7)
- DeepSeek v4 Pro (max) (#111, 51.6)
Compare it on the live leaderboard → · How the aggregate score works