Doubao-Seed-2.0 Pro (high): benchmark scores, price and ranking
Doubao-Seed-2.0 Pro (high) from ByteDance ranks #90 of 827 LLMs on the LLMs Tiger aggregate benchmark score (52.2), based on 4 benchmark results captured up to 2026-11-18.
- Organisation
- ByteDance
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-02-14 (source: epoch)
- Cheapest API price
- $0.482 in / $2.41 out per million tokens (via aihubmix, observed 2026-11-18T16:47Z)
- Aggregate rank
- #90 of 827 (score 52.2)
Relative to other models, Doubao-Seed-2.0 Pro (high) is strongest on OTIS Mock AIME (#44 of 206) and weakest on Chess Puzzles (#59 of 84).
Across the 4 benchmarks where at least ten models are scored, Doubao-Seed-2.0 Pro (high) is in the top 10% on 0 and in the top half on 2.
Its cheapest listed input price, $0.482 per million tokens, is lower than that of 50% of the 443 models with a listed price.
Doubao-Seed-2.0 Pro (high) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| OTIS Mock AIME | 93.9% | #44 of 206 | Epoch AI Benchmarking Hub | 2026-11-18 |
| GPQA Diamond | 88.2% | #70 of 302 | Epoch AI Benchmarking Hub | 2026-11-18 |
| SimpleQA Verified | 39.4% | #48 of 83 | Epoch AI Benchmarking Hub | 2026-11-18 |
| Chess Puzzles | 20.0% | #59 of 84 | Epoch AI Benchmarking Hub | 2026-11-18 |
About Doubao-Seed-2.0 Pro (high)
Doubao-Seed-2.0 Pro (high) is a frontier model from ByteDance. It was released on 2026-02-14, according to Epoch AI. The cheapest API listing we track charges $0.482 per million input tokens and $2.41 per million output tokens, through aihubmix. We hold 4 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where Doubao-Seed-2.0 Pro (high) stands
On our aggregate score, Doubao-Seed-2.0 Pro (high) is #90 of 827 ranked models, in the top quarter. Its score is 52.2; the scale is centred on 50, so it sits 2.2 points above the typical model. That beats 89% of the ranked field. Among the 7 ranked ByteDance models it is #3. The next one up is Doubao Seed 2.1 Pro (high) at 52.7. The next one down is Doubao Seed 2.1 Turbo (high) at 51.6.
Doubao-Seed-2.0 Pro (high), benchmark by benchmark
OTIS Mock AIME puts Doubao-Seed-2.0 Pro (high) at 93.9%, #44 of 206. That beats 79% of the models tested, but 6.1 points short of Claude Fable 5.1 (max) (100.0%). The results either side are DeepSeek V4 Flash 0731 (max) (94.4%) and GLM-5.3-Flash (max) (93.9%). It covers competition maths (AIME 2024-25 style). The board median is 66.4%, so Doubao-Seed-2.0 Pro (high) is 27.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
On GPQA Diamond, Doubao-Seed-2.0 Pro (high) reaches 88.2%. It ranks #70 of 302, ahead of 77% of the field, and 8.6 points behind GPT-6.2 Astra (max) at 96.8%. The results either side are Inkling (xhigh) (88.3%) and Doubao Seed 2.0 Lite (Apr 2026, high) (88.1%). It covers expert-level science questions. The board median is 75.1%, so Doubao-Seed-2.0 Pro (high) is 13.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
Doubao-Seed-2.0 Pro (high) lands below the middle on SimpleQA Verified: 39.4%, #48 of 83, with 57% of the field scoring higher. Claude Fable 5.2 (max) leads at 94.0%; the closest result above is Inkling (xhigh) at 40.3%. It covers short factual questions. The board median is 41.4%, so Doubao-Seed-2.0 Pro (high) is 2.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
Doubao-Seed-2.0 Pro (high) lands below the middle on Chess Puzzles: 20.0%, #59 of 84, with 69% of the field scoring higher. Claude Fable 5.2 (max) leads at 79.0%; the closest result above is Doubao Seed 2.0 Lite (Apr 2026, high) at 20.0%. It covers chess tactics puzzles. The board median is 33.0%, so Doubao-Seed-2.0 Pro (high) is 13.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-11-18.
Strengths and weaknesses
Reasoning, maths and science: strong, ahead of 78% of the field on average across 2 benchmarks. Its best board here is OTIS Mock AIME (#44 of 206) and its weakest is GPQA Diamond (#70 of 302). General knowledge and chat: uneven, ahead of 36% of the field on average across 2 benchmarks. Its best board here is SimpleQA Verified (#48 of 83) and its weakest is Chess Puzzles (#59 of 84).
Price and value
The median input price across the 443 priced models is $0.482 per million tokens, so Doubao-Seed-2.0 Pro (high) costs about the same as the typical listing. Models that score within 1.5 points or better and cost less: GLM-5.2 (high) ($0.0070, 51.6), DeepSeek V4.1 Flash 1017 (max) ($0.036, 55.5), DeepSeek V4 Flash 0731 (max) ($0.060, 52.3). Similar scores cost more on Gemini 3 Flash ($0.500) and SWE-1.7 ($0.500).
Release history
The next one was Doubao Seed 2.0 Lite (Apr 2026, high) on 2026-04-28, at 51.4.
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. With 4 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #87 Darwin-180B-RSI (52.2)
- #88 GPT-5.1 (high) (52.2)
- #89 Claude Opus 5.5 (with fallback, max) (52.2)
- #91 Antigravity CLI + Gemini 4 Hydrogen (52.2)
- #92 Intern-S2-Preview (52.2)
- #93 gemini-3.5-flash-high (52.2)
More from ByteDance
- Doubao Seed Evolving (Nov 2026, high) (#53, 52.9)
- Doubao Seed 2.1 Pro (high) (#64, 52.7)
- Doubao Seed 2.1 Turbo (high) (#137, 51.6)
- Doubao Seed 2.0 Lite (Apr 2026, high) (#152, 51.4)
- Doubao-Seed-1.6 (thinking) (#379, 48.7)
- seed-2.1-pro-preview (#527, 47.2)
Compare it on the live leaderboard → · How the aggregate score works