Benchmark Almanac

QwenClawBench

Qwen3.7-Max 64.3% leads since May 2026 Fading

Agents complete 100 tasks across 8 domains in isolated OpenClaw workspaces drawn from real user patterns. Automated checks and an LLM judge score each task.

Qwen built it as an internal benchmark for Qwen3.6-Plus and released it afterward.

Made by Qwen Team , Alibaba Group Released Apr 2026 General assistants All tasks public Last in a launch post Jun 2026 , dropped before it saturated Last model added Jun 2026
Level
Everyday Most adults, without training
Scored
Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers
Agent task Many steps in a terminal, browser, desktop, app, game or robot.
SKYLENAGE-AI/QwenClawBench 62 stars
6
Models scored in lab cards
6
Launch posts list it, from 1 lab

Qwen3.7-Max leads with 64.3% among models released by Jun 2026

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

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

  1. 64.3 Qwen3.7-Max
  2. 61.8 Qwen3.7-Plus
  3. 59.0 Qwen 3.6 Max (Preview)
  4. 57.2 Qwen 3.6 Plus
  5. 53.4 Qwen3.6 27B
  6. 52.6 Qwen 3.6 35B-A3B
  1. 1 Qwen3.7-Max 64.3%
  2. 2 Qwen3.7-Plus 61.8%
  3. 3 Qwen 3.6 Max (Preview) 59%
  4. 4 Qwen 3.6 Plus 57.2%
  5. 5 Qwen3.6 27B 53.4%
  6. 6 Qwen 3.6 35B-A3B 52.6%
#ModelScoreSettingDateSource
1 Qwen3.7-Max 64.3% May 2026 Model card
2 Qwen3.7-Plus 61.8% Jun 2026 Model card
3 Qwen 3.6 Max (Preview) 59% Apr 2026 Model card
4 Qwen 3.6 Plus 57.2% Apr 2026 Model card
5 Qwen3.6 27B 53.4% Apr 2026 Model card
6 Qwen 3.6 35B-A3B 52.6% Apr 2026 Model card

3 models have held number one since its release in Apr 2026

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

Qwen
Lab claims Not tested since Jun 2026
Qwen3.7-Max 64.3%

Scores over time

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

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Qwen3.7-Max Qwen 3.6 Max (Preview) 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Qwen3.7-Max Qwen 3.6 Plus

Labs headline it less often now, last in Jun 2026

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.

Qwen
DateLaunch postScoreAs the post writes it
1 Jun 2026 Qwen3.7-Plus 61.8 Qwenclaw
20 May 2026 Qwen3.7-Max 64.3 Qwenclaw
22 Apr 2026 Qwen3.6 27B 53.4 QwenClawBench
20 Apr 2026 Qwen 3.6 Max (Preview) 59 QwenClawBench Real-World Agent
15 Apr 2026 Qwen 3.6 35B-A3B 52.6 QwenClawBench
2 Apr 2026 Qwen 3.6 Plus 57.2 QwenClawBench

More in Tool use

All 125 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. Muse Spark 1.1 88.1%
  • 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%
  • Claw-Eval In use 300 human-verified agent tasks (service orchestration, multimodal, multi-turn dialogue) audited via traces and snapshots. Rubric scores with Pass^3 consistency. Claude Sonnet 4.6 81.4%
  • DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%