Benchmark Almanac

GEN-Bench

Qwen3-14B 6.09% leads since August 2025
Not in model cards

Agents select job operations as conditions change in a simulated factory. The benchmark compares schedule completion times with the best known result for each instance.

The RACE-Sched paper tested six model backends on both factory sizes. The released files contain 18 small instances and 20 normal instances.

Made by
Shijie Cao and Yuan Yuan
Released
August 2025
Kind
Tasks from real jobs
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Agentic
Environment
A simulator
Items from
Generated
Refresh
One fixed set
Run by
Anyone
In views
Agents, Robotics
Strongest model tested
DeepSeek-V3.2 #91 on the capability index
Last model added
December 2025
Scores refreshed
November 20th, 2026
12
Entries in its paper, 5 models we track

Qwen3-14B leads with 6.09% among models released by December 2025 Qwen3-14B leads with 6.09% among models released by December 2025

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Qwen3-14B 6.09%
  2. 2 Qwen3-32B 6.87%
  3. 3 Qwen3-8B 6.94%
  4. 4 GPT-4o (snapshot unspecified) 7.14%
  5. 5 DeepSeek-V3 (snapshot unspecified) 7.49%
  6. 6 DeepSeek-V3.2 7.74%
  7. 7 GPT-5 nano 8.03%
  8. 8 IDDQN 10.4%
  9. 9 DAN 10.7%
  10. 10 HMPSAC 11%
  11. 11 PPO-OC 13.5%
  12. 12 GP 54.9%

Source: The GEN-Bench paper

Source: The GEN-Bench paper

#EntryScoreSettingDateSource
1 Qwen3-14B 6.09% ReflecSched Apr 2025 Official leaderboard
2 Qwen3-32B 6.87% ReflecSched Apr 2025 Official leaderboard
3 Qwen3-8B 6.94% ReflecSched Apr 2025 Official leaderboard
4 GPT-4o (snapshot unspecified) 7.14% ReflecSched Official leaderboard
5 DeepSeek-V3 (snapshot unspecified) 7.49% ReflecSched Official leaderboard
6 DeepSeek-V3.2 7.74% ReflecSched Dec 2025 Official leaderboard
7 GPT-5 nano 8.03% ReflecSched Aug 2025 Official leaderboard
8 IDDQN 10.4% Official leaderboard
9 DAN 10.7% Official leaderboard
10 HMPSAC 11% Official leaderboard
11 PPO-OC 13.5% Official leaderboard
12 GP 54.9% Official leaderboard
#ModelScoreSettingDateSource
1 Qwen3-14B 6.09% ReflecSched Apr 2025 Official leaderboard
2 Qwen3-32B 6.87% ReflecSched Apr 2025 Official leaderboard
3 Qwen3-8B 6.94% ReflecSched Apr 2025 Official leaderboard
4 DeepSeek-V3.2 7.74% ReflecSched Dec 2025 Official leaderboard
5 GPT-5 nano 8.03% ReflecSched Aug 2025 Official leaderboard

Number one over time

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

Qwen
Benchmark paper Not tested since Dec 2025
Qwen3-14B 6.09%

Source: The GEN-Bench paper

Scores over time

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

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Qwen3-14B 0% 20% 40% 60% 80% 100% 2025 2026 Qwen3-14B

Source: Official GEN-Bench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 11 months ago, in December 2025, for DeepSeek-V3.2. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 5 models we track, plus 7 other entries on its leaderboard.
  • Warning Newest score The newest came 11 months ago, in December 2025, for DeepSeek-V3.2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek-V3.2 (#91).
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 5 rows for models we track and 7 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check