Benchmarks · Professional work · Agents & computer use
Corpo-Bench: Worker
Star0Corpo-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
Benchmark quality
How the score works- Overall67
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.
8 more models under All models in settings.
More from this benchmark
3 published measuresScore vs any published measure
9 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | ||
|---|---|---|
| GPT-6 Astra xhigh | 6.7 | 42.0 |
| Gemini 4 Hydrogen xhigh | 8.3 | 14.0 |
| GPT-6 Sol xhigh | 6 | 42.0 |
| Opus 5.5 xhigh | 9.3 | 42.0 |
| Sonnet 5.5 xhigh | 8.2 | 42.0 |
| GPT-6.1 Sol xhigh | 8.2 | 42.0 |
| Gemini 4 Neon xhigh | 11.6 | 14.0 |
| Gemini 4 Carbon high | 19.7 | 14.0 |
| GPT-6.2 Astra xhigh | 10.0 | 14.0 |
| Fable 5.1 xhigh | 10.3 | 42.0 |
| Fable 5.2 xhigh | 13.4 | 42.0 |
| DeepSeek V4.1 Flash high | 7.2 | 42.0 |
| GPT-6 Luna xhigh | 4.5 | 42.0 |
| GPT-6.2 Sol xhigh | 5.9 | 14.0 |
| Haiku 5.5 xhigh | 9.3 | 42.0 |
| GPT-6.1 Terra xhigh | 1 | 42.0 |
| Opus 4.6 max | 18.3 | 42.0 |
| GLM 5.3 Flash high | 2.6 | 42.0 |
| Hy4 preview high | 16.2 | 42.0 |
| MiniMax M3.1 xhigh | 12.6 | 42.0 |
| Hy4 Flash high | 4 | 14.0 |
| Muse Ember xhigh | 2.4 | 42.0 |
| Sonnet 5 xhigh | 12.5 | 42.0 |
All results
23 rows| # | Model | Effort | Corpo-Bench: Worker | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | xhigh | 73.7 ±3.2 | $0.070 | $1.96 |
| 2 | Gemini 4 Hydrogen | xhigh | 72.1 ±5.6 | $0.039 | $1.92 |
| 3 | GPT-6 Sol | xhigh | 72.0 ±4.5 | $0.018 | $0.57 |
| 4 | Opus 5.5 | xhigh | 71.8 ±5.5 | $0.037 | $2.82 |
| 5 | Sonnet 5.5 | xhigh | 71.8 ±5.7 | $0.025 | $1.95 |
| 6 | GPT-6.1 Sol | xhigh | 71.3 ±4.9 | $0.012 | $0.37 |
| 7 | Gemini 4 Neon | xhigh | 71.1 ±6.1 | $0.057 | $2.74 |
| 8 | Gemini 4 Carbon | high | 70.7 ±7.3 | $0.18 | $3.03 |
| 9 | GPT-6.2 Astra | xhigh | 70.4 ±5.9 | $0.080 | $1.20 |
| 10 | Fable 5.1 | xhigh | 70.2 ±5.8 | $0.90 | $5.78 |
| 11 | Fable 5.2 | xhigh | 69.9 ±5.1 | $0.25 | $6.78 |
| 12 | DeepSeek V4.1 Flash | high | 69.9 ±4.6 | $0.017 | $0.17 |
| 13 | GPT-6 Luna | xhigh | 69.4 ±5.2 | $0.007 | $0.090 |
| 14 | GPT-6.2 Sol | xhigh | 69.3 ±6.6 | $0.012 | $0.37 |
| 15 | Haiku 5.5 | xhigh | 69.2 ±5.5 | $0.012 | $0.65 |
| 16 | GPT-6.1 Terra | xhigh | 69.2 ±5.4 | $0.004 | $0.11 |
| 17 | Opus 4.6 | max | 68.3 ±4.7 | $4.10 | $4.10 |
| 18 | GLM 5.3 Flash | high | 68.1 ±5.8 | $0.033 | $0.20 |
| 19 | Hy4 preview | high | 67.1 ±5.1 | $0.33 | $1.00 |
| 20 | MiniMax M3.1 | xhigh | 66.9 ±4.5 | $0.11 | $0.22 |
| 21 | Hy4 Flash | high | 66.8 ±6.4 | $0.030 | $0.030 |
| 22 | Muse Ember | xhigh | 65.7 ±4.9 | $0.080 | $0.080 |
| 23 | Sonnet 5 | xhigh | 63.9 ±6.1 | $0.032 | $3.16 |