Support

Benchmarks · Professional work · Agents & computer use

Corpo-Bench: Worker

Star0

Corpo-Bench's Worker role: a fixed Opus 5.5 orchestrator writes the work order and reviews the result once, and the model does the work. Not part of the Corpo Index.

Quality 67 of 100 · Private test set · Has measured 10 of today's 10 default lineup models

23 models · 23 results · updated 2026-11-19 · local-bench.ai ↗

Leaderboard

GPT-6 Astra xhigh

Benchmark quality

How the score works
  • Overall
    67

    67 of 100

    How useful it is for telling today’s models apart

  • Headroom20%
    23

    Top models average 72 of 100

    Can top models still improve on it?

  • Test set20%
    100

    Private

    Could labs train on the questions?

  • Recency15%
    100

    36 days old

    How new is it?

  • Grading15%
    65

    Not researched

    How are answers scored?

  • New models15%
    100

    10 of 10 top models

    How fast does it test new releases?

  • Efforts10%
    0

    One effort per model

    Does it test each model at several reasoning efforts?

  • Breadth5%
    57

    23 models

    How many models has it measured?

How each part was worked out
Headroom 23 of 100 · 20% · +4.6
From the spread of published scores and the room left above the top quarter of models, one score per model.
Test set 100 of 100 · 20% · +20
Private test set. The 14 consulting-style tasks were built for the benchmark and are not published; the method page describes them but shows none. Source
Recency 100 of 100 · 15% · +15
Released 2026-10-17 (from the publisher's pages, not yet checked by hand).
Grading 65 of 100 · 15% · +9.8
Judged from its unit and description; the grading method has not been researched.
New models 100 of 100 · 15% · +15
Has measured 10 of today's 10 default lineup models. Too few new models to time how quickly it adds them.
Efforts 0 of 100 · 10% · 0
Measured 0 of the 23 models that come in more than one reasoning effort at two or more of them.
Breadth 57 of 100 · 5% · +2.9
23 models measured.

Not counted in the score: 0 stars · used by 0 published pages. Both lift it in the directory’s recommended order. Test set, release date and grading were researched from the publisher’s pages (2026-11-19); tell us if one is wrong.

Score vs subscription cost per task

Highlight models

Click a point on the chart to highlight that exact effort; click it again to remove it.

8 more models under All models in settings.

More from this benchmark

3 published measures

Breakdown

darker is better within each column · click a column to sort

All results

23 rows
#ModelEffortCorpo-Bench: WorkerSubscription $ / taskAPI $ / task
1GPT-6 Astraxhigh73.7 ±3.2$0.070$1.96
2Gemini 4 Hydrogenxhigh72.1 ±5.6$0.039$1.92
3GPT-6 Solxhigh72.0 ±4.5$0.018$0.57
4Opus 5.5xhigh71.8 ±5.5$0.037$2.82
5Sonnet 5.5xhigh71.8 ±5.7$0.025$1.95
6GPT-6.1 Solxhigh71.3 ±4.9$0.012$0.37
7Gemini 4 Neonxhigh71.1 ±6.1$0.057$2.74
8Gemini 4 Carbonhigh70.7 ±7.3$0.18$3.03
9GPT-6.2 Astraxhigh70.4 ±5.9$0.080$1.20
10Fable 5.1xhigh70.2 ±5.8$0.90$5.78
11Fable 5.2xhigh69.9 ±5.1$0.25$6.78
12DeepSeek V4.1 Flashhigh69.9 ±4.6$0.017$0.17
13GPT-6 Lunaxhigh69.4 ±5.2$0.007$0.090
14GPT-6.2 Solxhigh69.3 ±6.6$0.012$0.37
15Haiku 5.5xhigh69.2 ±5.5$0.012$0.65
16GPT-6.1 Terraxhigh69.2 ±5.4$0.004$0.11
17Opus 4.6max68.3 ±4.7$4.10$4.10
18GLM 5.3 Flashhigh68.1 ±5.8$0.033$0.20
19Hy4 previewhigh67.1 ±5.1$0.33$1.00
20MiniMax M3.1xhigh66.9 ±4.5$0.11$0.22
21Hy4 Flashhigh66.8 ±6.4$0.030$0.030
22Muse Emberxhigh65.7 ±4.9$0.080$0.080
23Sonnet 5xhigh63.9 ±6.1$0.032$3.16