Benchmarks · Human preference
PriorsBench
Star0What Priors visitors think: each ranking people finish on Priors counts every higher-placed model as beating every lower one, fitted into an Elo-scale rating like an arena, with recent rankings counting most. A measure of belief, not ability; never in a default mix.
Quality 71 of 100 · Private test set, with questions replaced on a schedule · Has measured 10 of today's 10 default lineup models
41 models · 41 results · updated 2026-11-22 · mypriors.com ↗
Leaderboard
Benchmark quality
How the score works- Overall71
71 of 100
How useful it is for telling today’s models apart
- Headroom20%50
Some room left
Can top models still improve on it?
- Test set20%100
Private, refreshed
Could labs train on the questions?
- Recency15%100
0 days old
How new is it?
- Grading15%40
People vote
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%100
41 models
How many models has it measured?
How each part was worked out
- Headroom 50 of 100 · 20% · +10
- 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, with questions replaced on a schedule. There is no test set: the votes are the rankings people finish on Priors, which keep arriving. Source
- Recency 100 of 100 · 15% · +15
- Released 2026-11-22 (from the publisher's pages, not yet checked by hand).
- Grading 40 of 100 · 15% · +6
- Ranked by people's votes.
- 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 41 models that come in more than one reasoning effort at two or more of them.
- Breadth 100 of 100 · 5% · +5
- 41 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.
More from this benchmark
2 published measuresScore vs any published measure
25 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | ||
|---|---|---|
| Fable 5.2 | 354.0 | 310.3 |
| Gemini 4 Neon | 138.0 | 131.5 |
| Opus 5.5 | 1,487 | 787.5 |
| GPT-6.2 Astra | 167.0 | 157.5 |
| Gemini 4 Carbon | 765.0 | 508.5 |
| GPT-6.2 Sol | 168.0 | 157.7 |
| GPT-6 Astra | 1,474 | 775.1 |
| Sonnet 5.5 | 1,418 | 755.5 |
| GPT-6.1 Sol | 1,439 | 773.5 |
| Gemini 4 Hydrogen | 272.0 | 243.2 |
| GPT-6.1 Terra | 837.0 | 549.2 |
| Fable 5.1 | 1,432 | 744.6 |
| Gemini 4 Argon | 1,352 | 719.8 |
| Muse Wonder Full | 1,166 | 637.0 |
| Kimi K3.1 | 839.0 | 538.2 |
| Fable 5 | 656.0 | 235.7 |
| Opus 5 | 969.0 | 480.0 |
| Muse Wonder | 1,030 | 512.0 |
| GPT-6 Sol | 1,124 | 560.5 |
| Gemini 3.7 Flash | 36.0 | 19.3 |
| GPT-5.5 | 28.0 | 10.0 |
| Muse Spark 1.3 | 1,150 | 520.2 |
| GPT-5.6 Sol | 675.0 | 258.1 |
| DeepSeek V4.1 Flash | 78.0 | 35.0 |
| Opus 4.8 | 40.0 | 19.7 |
All results
41 rows| # | Model | Effort | PriorsBench |
|---|---|---|---|
| 1 | Fable 5.2 | 2020 ±63 | |
| 2 | Gemini 4 Neon | 1822 ±61 | |
| 3 | Opus 5.5 | 1757 ±34 | |
| 4 | GPT-6.2 Astra | 1718 ±59 | |
| 5 | Gemini 4 Carbon | 1519 ±37 | |
| 6 | GPT-6.2 Sol | 1501 ±35 | |
| 7 | GPT-6 Astra | 1470 ±30 | |
| 8 | Sonnet 5.5 | 1342 ±29 | |
| 9 | GPT-6.1 Sol | 1302 ±29 | |
| 10 | Gemini 4 Hydrogen | 1215 ±36 | |
| 11 | GPT-6.1 Terra | 1146 ±33 | |
| 12 | Fable 5.1 | 1142 ±35 | |
| 13 | Gemini 4 Argon | 1106 ±30 | |
| 14 | Muse Wonder Full | 1087 ±32 | |
| 15 | Kimi K3.1 | 895 ±38 | |
| 16 | Fable 5 | 804 ±36 | |
| 17 | Opus 5 | 776 ±39 | |
| 18 | Muse Wonder | 711 ±39 | |
| 19 | GPT-6 Sol | 711 ±40 | |
| 20 | Gemini 3.7 Flash | 636 ±177 | |
| 21 | GPT-5.5 | 608 ±87 | |
| 22 | Muse Spark 1.3 | 545 ±49 | |
| 23 | GPT-5.6 Sol | 505 ±50 | |
| 24 | DeepSeek V4.1 Flash | 499 ±93 | |
| 25 | Opus 4.8 | 474 ±118 | |
| 26 | Qwen 4 Max | 455 ±115 | |
| 27 | Gemini 3.8 Flash | 432 ±125 | |
| 28 | Haiku 5.5 | 427 ±58 | |
| 29 | GLM 5.3 Flash | 416 ±131 | |
| 30 | Grok 4.7 | 367 ±56 |