Benchmark Almanac

SeedClawBench

Seed2.1 Pro 66.6% leads since June 2026
In use

Agents complete 100 OpenClaw-style user tasks built from Ark usage logs and crowdsourced tasks, such as data analysis and office work. An agent judge checks rubric items against the trace and deliverables.

In-house Seed benchmark. The card reports 89.69% agreement between the agent judge and humans on 262 rubric items. The launch blog calls it ClawBench.

Made by
ByteDance Seed
Released
June 2026
Kind
General assistants
Level
Everyday
Scored
Graded by a model
Answers
Agent task
Tasks
Kept private
Strongest model tested
GPT-5.5 #20 on the capability index
Last in a launch post
June 2026
Last model added
June 2026
Scores refreshed
November 12th, 2026
5
Models scored on its own leaderboard
1
Launch post lists it, from 1 lab
1
System card reports it, from 1 lab

Seed2.1 Pro leads with 66.6% among models released by June 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 66.6 Seed2.1 Pro
  2. 66.4 GPT-5.5
  3. 64.1 Claude Opus 4.7
  4. 63.8 Doubao Seed 2.1 Turbo
  5. 57.1 Gemini 3.1 Pro
  1. 1 Seed2.1 Pro 66.6%
  2. 2 GPT-5.5 66.4%
  3. 3 Claude Opus 4.7 64.1%
  4. 4 Doubao Seed 2.1 Turbo 63.8%
  5. 5 Gemini 3.1 Pro 57.1%

Source: Official SeedClawBench leaderboard

#ModelScoreSettingDateSource
1 Seed2.1 Pro 66.6% Jun 2026 Official leaderboard
2 GPT-5.5 66.4% Apr 2026 Official leaderboard
3 Claude Opus 4.7 64.1% Apr 2026 Official leaderboard
4 Doubao Seed 2.1 Turbo 63.8% Jun 2026 Official leaderboard
5 Gemini 3.1 Pro 57.1% Feb 2026 Official leaderboard

Labs report scores for 1 model in their cards. We plot every source in the charts below.

2 models have held number one on the official leaderboard since its release in June 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI ByteDance Seed
Own leaderboard Not tested since Jun 2026
Seed2.1 Pro 66.6%

Source: Official SeedClawBench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Seed2.1 Pro GPT-5.5 Gemini 3.1 Pro 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Seed2.1 Pro Gemini 3.1 Pro

Sources: Official SeedClawBench leaderboard and labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

ByteDance Seed
DateLaunch postScoreAs the post writes it
Jun 23, 2026 Seed2.1 Pro 66.6 SeedClawBench (blog: ClawBench)

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Jun 23, 2026 Seed2.1 Pro model card 66.6 SeedClawBench, Pass@1 (Table 2) Capabilities

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Seed2.1 Pro 66.6% SeedClawBench (blog: ClawBench) 66.6% Leaderboard Same

More in Tool use

All 144 in Tool use
  • AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Carbon 53.9%
  • MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
  • BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
  • τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
  • Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%