Benchmarks · Professional work · Agents & computer use
Corpo Index: Orchestrator
Star0Corpo-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
Benchmark quality
How the score works- Overall69
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.
10 more models under All models in settings.
More from this benchmark
4 published measuresScore vs any published measure
10 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | |||
|---|---|---|---|
| Opus 5.5 xhigh | 9.1 | 29.0 | 14.0 |
| GPT-6.2 Astra xhigh | 5.5 | 28.0 | 14.0 |
| Sonnet 5.5 xhigh | 5.8 | 29.0 | 14.0 |
| GPT-6.1 Sol xhigh | 7.9 | 29.0 | 14.0 |
| Fable 5.1 xhigh | 9.8 | 28.0 | 14.0 |
| Gemini 4 Carbon high | 13.3 | 30.0 | 14.0 |
| GPT-6.2 Sol xhigh | 3.1 | 30.0 | 14.0 |
| Fable 5.2 xhigh | 11.9 | 31.0 | 14.0 |
| GPT-6 Astra xhigh | 7.2 | 31.0 | 14.0 |
| GPT-6 Sol xhigh | 2.5 | 30.0 | 14.0 |
| Gemini 4 Neon xhigh | 8.7 | 28.0 | 14.0 |
| Gemini 4 Hydrogen xhigh | 4.4 | 29.0 | 14.0 |
| DeepSeek V4.1 Flash high | 7.4 | 29.0 | 14.0 |
| Haiku 5.5 xhigh | 8.7 | 31.0 | 14.0 |
| Hy4 preview high | 8.9 | 27.0 | 13.0 |
| GPT-6.1 Terra xhigh | 0.8 | 29.0 | 14.0 |
| GLM 5.3 Flash high | 1.5 | 30.0 | 14.0 |
| MiniMax M3.1 xhigh | 5.3 | 30.0 | 14.0 |
| GPT-6 Luna xhigh | 2.6 | 29.0 | 14.0 |
| Muse Ember xhigh | 0.8 | 29.0 | 14.0 |
| Hy4 Flash high | 2 | 28.0 | 13.0 |
| Sonnet 5 xhigh | 9.8 | 31.0 | 14.0 |
| Opus 4.6 max | 5.3 | 29.0 | 14.0 |
All results
23 rows| # | Model | Effort | Score | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | Opus 5.5 | xhigh | 68.8 ±6.2 | $0.020 | $1.52 |
| 2 | GPT-6.2 Astra | xhigh | 66.6 ±7.5 | $0.035 | $0.52 |
| 3 | Sonnet 5.5 | xhigh | 63.8 ±7.3 | $0.009 | $0.68 |
| 4 | GPT-6.1 Sol | xhigh | 63.1 ±7.0 | $0.008 | $0.23 |
| 5 | Fable 5.1 | xhigh | 62.0 ±6.0 | $0.45 | $2.89 |
| 6 | Gemini 4 Carbon | high | 61.8 ±6.2 | $0.11 | $1.76 |
| 7 | GPT-6.2 Sol | xhigh | 61.5 ±7.8 | $0.006 | $0.17 |
| 8 | Fable 5.2 | xhigh | 61.4 ±9.6 | $0.15 | $4.08 |
| 9 | GPT-6 Astra | xhigh | 59.2 ±10.6 | $0.037 | $1.05 |
| 10 | GPT-6 Sol | xhigh | 58.9 ±6.1 | $0.006 | $0.19 |
| 11 | Gemini 4 Neon | xhigh | 58.4 ±10.5 | $0.023 | $1.11 |
| 12 | Gemini 4 Hydrogen | xhigh | 58.2 ±6.6 | $0.010 | $0.49 |
| 13 | DeepSeek V4.1 Flash | high | 58.1 ±6.6 | $0.011 | $0.11 |
| 14 | Haiku 5.5 | xhigh | 57.7 ±7.4 | $0.002 | $0.12 |
| 15 | Hy4 preview | high | 55.6 ±6.7 | $0.090 | $0.27 |
| 16 | GPT-6.1 Terra | xhigh | 55.5 ±8.0 | $0.002 | $0.050 |
| 17 | GLM 5.3 Flash | high | 54.7 ±5.5 | $0.005 | $0.030 |
| 18 | MiniMax M3.1 | xhigh | 54.6 ±5.6 | $0.020 | $0.040 |
| 19 | GPT-6 Luna | xhigh | 53.9 ±5.9 | $0.001 | $0.010 |
| 20 | Muse Ember | xhigh | 53.5 ±6.1 | $0.020 | $0.020 |
| 21 | Hy4 Flash | high | 53.3 ±6.3 | $0.010 | $0.010 |
| 22 | Sonnet 5 | xhigh | 51.1 ±4.4 | $0.007 | $0.74 |
| 23 | Opus 4.6 | max | 48.9 ±6.2 | $0.62 | $0.62 |