Support

Benchmarks · Professional work · Agents & computer use

Corpo Index: Orchestrator

Star0

Corpo-Bench's Orchestrator role: the model plans each task and writes one work order, and a fixed GPT-6 Luna worker does the work with no review. Tests delegation.

Quality 69 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

Opus 5.5 xhigh

Benchmark quality

How the score works
  • Overall
    69

    69 of 100

    How useful it is for telling today’s models apart

  • Headroom20%
    32

    Top models average 64 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 32 of 100 · 20% · +6.4
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.

10 more models under All models in settings.

More from this benchmark

4 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Opus 5.5 xhigh9.129.014.0
GPT-6.2 Astra xhigh5.528.014.0
Sonnet 5.5 xhigh5.829.014.0
GPT-6.1 Sol xhigh7.929.014.0
Fable 5.1 xhigh9.828.014.0
Gemini 4 Carbon high13.330.014.0
GPT-6.2 Sol xhigh3.130.014.0
Fable 5.2 xhigh11.931.014.0
GPT-6 Astra xhigh7.231.014.0
GPT-6 Sol xhigh2.530.014.0
Gemini 4 Neon xhigh8.728.014.0
Gemini 4 Hydrogen xhigh4.429.014.0
DeepSeek V4.1 Flash high7.429.014.0
Haiku 5.5 xhigh8.731.014.0
Hy4 preview high8.927.013.0
GPT-6.1 Terra xhigh0.829.014.0
GLM 5.3 Flash high1.530.014.0
MiniMax M3.1 xhigh5.330.014.0
GPT-6 Luna xhigh2.629.014.0
Muse Ember xhigh0.829.014.0
Hy4 Flash high228.013.0
Sonnet 5 xhigh9.831.014.0
Opus 4.6 max5.329.014.0

All results

23 rows
#ModelEffortScoreSubscription $ / taskAPI $ / task
1Opus 5.5xhigh68.8 ±6.2$0.020$1.52
2GPT-6.2 Astraxhigh66.6 ±7.5$0.035$0.52
3Sonnet 5.5xhigh63.8 ±7.3$0.009$0.68
4GPT-6.1 Solxhigh63.1 ±7.0$0.008$0.23
5Fable 5.1xhigh62.0 ±6.0$0.45$2.89
6Gemini 4 Carbonhigh61.8 ±6.2$0.11$1.76
7GPT-6.2 Solxhigh61.5 ±7.8$0.006$0.17
8Fable 5.2xhigh61.4 ±9.6$0.15$4.08
9GPT-6 Astraxhigh59.2 ±10.6$0.037$1.05
10GPT-6 Solxhigh58.9 ±6.1$0.006$0.19
11Gemini 4 Neonxhigh58.4 ±10.5$0.023$1.11
12Gemini 4 Hydrogenxhigh58.2 ±6.6$0.010$0.49
13DeepSeek V4.1 Flashhigh58.1 ±6.6$0.011$0.11
14Haiku 5.5xhigh57.7 ±7.4$0.002$0.12
15Hy4 previewhigh55.6 ±6.7$0.090$0.27
16GPT-6.1 Terraxhigh55.5 ±8.0$0.002$0.050
17GLM 5.3 Flashhigh54.7 ±5.5$0.005$0.030
18MiniMax M3.1xhigh54.6 ±5.6$0.020$0.040
19GPT-6 Lunaxhigh53.9 ±5.9$0.001$0.010
20Muse Emberxhigh53.5 ±6.1$0.020$0.020
21Hy4 Flashhigh53.3 ±6.3$0.010$0.010
22Sonnet 5xhigh51.1 ±4.4$0.007$0.74
23Opus 4.6max48.9 ±6.2$0.62$0.62