Benchmarks · Professional work · Agents & computer use
Corpo Index: Solo
Star0Corpo-Bench's Solo role: the model does each of the 14 consulting-style tasks alone, in its own harness, and two blind graders mark the deliverable out of 10.
Quality 68 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- Overall68
68 of 100
How useful it is for telling today’s models apart
- Headroom20%27
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 27 of 100 · 20% · +5.4
- 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.
11 more models under All models in settings.
More from this benchmark
3 published measuresScore vs any published measure
11 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | |||
|---|---|---|---|
| GPT-6.2 Astra xhigh | 8.4 | 29.0 | 14.0 |
| GPT-6.2 Sol xhigh | 5.1 | 28.0 | 14.0 |
| Fable 5.2 xhigh | 14.1 | 28.0 | 14.0 |
| Opus 5.5 xhigh | 9.1 | 28.0 | 14.0 |
| GPT-6 Astra xhigh | 7.5 | 29.0 | 14.0 |
| GPT-6.1 Sol xhigh | 9.1 | 29.0 | 14.0 |
| Sonnet 5.5 xhigh | 6.3 | 29.0 | 14.0 |
| GPT-6 Sol xhigh | 8.9 | 29.0 | 14.0 |
| Gemini 4 Neon xhigh | 15.3 | 28.0 | 14.0 |
| GPT-6.1 Terra xhigh | 0.8 | 31.0 | 14.0 |
| Gemini 4 Hydrogen xhigh | 9.1 | 28.0 | 14.0 |
| Haiku 5.5 xhigh | 7.3 | 28.0 | 14.0 |
| Gemini 4 Carbon high | 20.3 | 28.0 | 14.0 |
| Fable 5.1 xhigh | 9.1 | 29.0 | 14.0 |
| DeepSeek V4.1 Flash high | 6.3 | 29.0 | 14.0 |
| GPT-6 Luna xhigh | 3.1 | 29.0 | 14.0 |
| GLM 5.3 Flash high | 1.8 | 29.0 | 14.0 |
| Hy4 preview high | 13.1 | 27.0 | 13.0 |
| Muse Ember xhigh | 1.7 | 32.0 | 14.0 |
| MiniMax M3.1 xhigh | 9.9 | 30.0 | 14.0 |
| Hy4 Flash high | 2.9 | 30.0 | 13.0 |
| Sonnet 5 xhigh | 10.3 | 28.0 | 14.0 |
| Opus 4.6 max | 9.6 | 28.0 | 14.0 |
All results
23 rows| # | Model | Effort | Corpo Index: Solo | Subscription $ / task | API $ / task |
|---|---|---|---|---|---|
| 1 | GPT-6.2 Astra | xhigh | 73.5 ±6.1 | $0.067 | $1.00 |
| 2 | GPT-6.2 Sol | xhigh | 72.9 ±5.6 | $0.010 | $0.31 |
| 3 | Fable 5.2 | xhigh | 72.5 ±5.8 | $0.23 | $6.28 |
| 4 | Opus 5.5 | xhigh | 72.5 ±4.5 | $0.027 | $2.09 |
| 5 | GPT-6 Astra | xhigh | 71.5 ±7.0 | $0.057 | $1.60 |
| 6 | GPT-6.1 Sol | xhigh | 69.0 ±7.8 | $0.011 | $0.32 |
| 7 | Sonnet 5.5 | xhigh | 68.9 ±4.9 | $0.014 | $1.10 |
| 8 | GPT-6 Sol | xhigh | 67.4 ±6.1 | $0.012 | $0.38 |
| 9 | Gemini 4 Neon | xhigh | 66.6 ±5.4 | $0.046 | $2.20 |
| 10 | GPT-6.1 Terra | xhigh | 64.7 ±5.0 | $0.002 | $0.060 |
| 11 | Gemini 4 Hydrogen | xhigh | 64.5 ±4.6 | $0.021 | $1.05 |
| 12 | Haiku 5.5 | xhigh | 64.3 ±7.0 | $0.006 | $0.31 |
| 13 | Gemini 4 Carbon | high | 64.1 ±5.7 | $0.20 | $3.32 |
| 14 | Fable 5.1 | xhigh | 62.7 ±5.7 | $0.59 | $3.80 |
| 15 | DeepSeek V4.1 Flash | high | 60.7 ±6.3 | $0.014 | $0.14 |
| 16 | GPT-6 Luna | xhigh | 58.6 ±4.9 | $0.001 | $0.020 |
| 17 | GLM 5.3 Flash | high | 54.9 ±6.1 | $0.008 | $0.050 |
| 18 | Hy4 preview | high | 54.7 ±5.4 | $0.17 | $0.50 |
| 19 | Muse Ember | xhigh | 54.3 ±5.4 | $0.050 | $0.050 |
| 20 | MiniMax M3.1 | xhigh | 52.8 ±5.2 | $0.070 | $0.14 |
| 21 | Hy4 Flash | high | 51.5 ±5.3 | $0.010 | $0.010 |
| 22 | Sonnet 5 | xhigh | 50.7 ±7.1 | $0.012 | $1.23 |
| 23 | Opus 4.6 | max | 49.3 ±6.6 | $1.90 | $1.90 |