TimelineBench
Agents turn raw footage and a client brief into a finished video. The edit must pass delivery checks, meet the brief, and clear a quality threshold.
The authors calibrated the quality threshold against professional editors. They release the verifier and task briefs but retain the licensed source footage.
- Made by
- TensorTest
- Released
- September 2026
- Kind
- Tasks from real jobs
- Level
- University
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Arts
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use, Written by experts
- Refresh
- One fixed set
- Run by
- A host
- Occupations
- Arts, design, entertainment, sports and media
- In views
- Agents, Vision, Audio and speech, Image, video and 3D generation
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 32.1% among models released by September 2026 Claude Opus 5.5 leads with 32.1% among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- 1 Claude Opus 5.5 guidance off, max ✓ 32.1%
- 2 GPT-6 Astra guidance curated, max ✓ 26.8%
- 3 GPT-6.1 Sol guidance off, max ✓ 25%
- 4 Claude Opus 5 guidance off, max ✓ 23.2%
- 5 Claude Sonnet 5.5 guidance off, max ✓ 21.4%
- 6 GPT-5.6 Sol guidance off, max ✓ 17.9%
- 7 Claude Fable 5.1 guidance off, max ✓ 17.9%
- 8 Grok 4.6 guidance off, xhigh ✓ 12.5%
- 9 GLM-5.3-Flash guidance off, max ✓ 10.7%
- 10
Gemini 3.8 Flash guidance off, high (thinking level) ✓ 10.7%
- 11 DeepSeek Flash guidance off, max ✓ 7.14%
- 12
Qwen 3.8 Max guidance off, xhigh ✓ 3.57%
- 13
Gemini 3.1 Pro guidance off, high (thinking level) ✓ 1.79%
Source: Official TimelineBench leaderboard
- 1 Claude Opus 5.5 guidance off, max ✓ 32.1%
- 2 GPT-6 Astra guidance curated, max ✓ 26.8%
- 3 GPT-6.1 Sol guidance off, max ✓ 25%
- 4 Claude Opus 5 guidance off, max ✓ 23.2%
- 5 Claude Sonnet 5.5 guidance off, max ✓ 21.4%
- 6 GPT-5.6 Sol guidance off, max ✓ 17.9%
- 7 Claude Fable 5.1 guidance off, max ✓ 17.9%
- 8 Grok 4.6 guidance off, xhigh ✓ 12.5%
- 9 GLM-5.3-Flash guidance off, max ✓ 10.7%
- 10
Gemini 3.8 Flash guidance off, high (thinking level) ✓ 10.7%
- 11
Qwen 3.8 Max guidance off, xhigh ✓ 3.57%
- 12
Gemini 3.1 Pro guidance off, high (thinking level) ✓ 1.79%
Source: Official TimelineBench leaderboard
| # | Entry | Score ± | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 ✓ | 32.1% 20.3 to 46 | guidance off, max, Claude Code | Sep 2026 | Oct 2026 | timelinebench.tensortest.com | Official leaderboard |
| 2 | GPT-6 Astra ✓ | 26.8% 15.8 to 40.3 | guidance curated, max, Codex | Sep 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 3 | GPT-6.1 Sol ✓ | 25% 14.4 to 38.4 | guidance off, max, Codex | Sep 2026 | Oct 2026 | timelinebench.tensortest.com | Official leaderboard |
| 4 | Claude Opus 5 ✓ | 23.2% 13 to 36.4 | guidance off, max, Claude Code | Jul 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 5 | Claude Sonnet 5.5 ✓ | 21.4% 11.6 to 34.4 | guidance off, max, Claude Code | Sep 2026 | Oct 2026 | timelinebench.tensortest.com | Official leaderboard |
| 6 | GPT-5.6 Sol ✓ | 17.9% 8.9 to 30.4 | guidance off, max, OpenCode | Jul 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 7 | Claude Fable 5.1 ✓ | 17.9% 8.9 to 30.4 | guidance off, max, Claude Code | Sep 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 8 | Grok 4.6 ✓ | 12.5% 5.2 to 24.1 | guidance off, xhigh, OpenCode | Aug 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 9 | GLM-5.3-Flash ✓ | 10.7% 4 to 21.9 | guidance off, max, OpenCode | Aug 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 10 | | 10.7% 4 to 21.9 | guidance off, high (thinking level), OpenCode | Sep 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 11 | DeepSeek Flash ✓ | 7.14% 2 to 17.3 | guidance off, max, OpenCode | Sep 2026 | timelinebench.tensortest.com | Official leaderboard | |
| 12 | | 3.57% 0.4 to 12.3 | guidance off, xhigh, OpenCode | Aug 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 13 | | 1.79% 0 to 9.6 | guidance off, high (thinking level), OpenCode | Feb 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| # | Model | Score ± | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 ✓ | 32.1% 20.3 to 46 | guidance off, max, Claude Code | Sep 2026 | Oct 2026 | timelinebench.tensortest.com | Official leaderboard |
| 2 | GPT-6 Astra ✓ | 26.8% 15.8 to 40.3 | guidance curated, max, Codex | Sep 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 3 | GPT-6.1 Sol ✓ | 25% 14.4 to 38.4 | guidance off, max, Codex | Sep 2026 | Oct 2026 | timelinebench.tensortest.com | Official leaderboard |
| 4 | Claude Opus 5 ✓ | 23.2% 13 to 36.4 | guidance off, max, Claude Code | Jul 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 5 | Claude Sonnet 5.5 ✓ | 21.4% 11.6 to 34.4 | guidance off, max, Claude Code | Sep 2026 | Oct 2026 | timelinebench.tensortest.com | Official leaderboard |
| 6 | GPT-5.6 Sol ✓ | 17.9% 8.9 to 30.4 | guidance off, max, OpenCode | Jul 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 7 | Claude Fable 5.1 ✓ | 17.9% 8.9 to 30.4 | guidance off, max, Claude Code | Sep 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 8 | Grok 4.6 ✓ | 12.5% 5.2 to 24.1 | guidance off, xhigh, OpenCode | Aug 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 9 | GLM-5.3-Flash ✓ | 10.7% 4 to 21.9 | guidance off, max, OpenCode | Aug 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 10 | | 10.7% 4 to 21.9 | guidance off, high (thinking level), OpenCode | Sep 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 11 | | 3.57% 0.4 to 12.3 | guidance off, xhigh, OpenCode | Aug 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
| 12 | | 1.79% 0 to 9.6 | guidance off, high (thinking level), OpenCode | Feb 2026 | Sep 2026 | timelinebench.tensortest.com | Official leaderboard |
3 models have held number one on the official leaderboard since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official TimelineBench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official TimelineBench 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
- 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
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (13 entries).
- Pass Models scored 12 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
- Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 32.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on timelinebench.tensortest.com: 18 rows for models we track and 1 other entry 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.