Guesswork (The Aggregate)
Models predict benchmark scores before publication. The maker ranks forecasts by mean absolute error after scaling each error by the variation in that benchmark’s scores.
The maker ranks 32 language models on 124 shared predictions in November. A separate statistical predictor competes on the same information.
- Released
- June 2026
- Kind
- Real-world events
- Level
- University
- Scored
- Settled by events
- Answers
- Prediction
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Environment
- The live world
- Items from
- Live play or votes
- Refresh
- Live
- Run by
- A host
- In views
- Kept fresh
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
GPT-6 Astra leads with 0.56 among models released by September 2026 GPT-6 Astra leads with 0.56 among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- 1 GPT-6 Astra 2026-11 0.56
- 2 GPT-6.1 Sol 2026-11 0.56
- 3 Claude Opus 5.5 2026-11 0.57
- 4 Claude Fable 5.1 2026-11 0.60
- 5 Claude Sonnet 5.5 2026-11 0.64
- 6 Claude Opus 5 2026-11 0.65
- 7 Claude Opus 4.8 2026-11 0.68
- 8
Gemini 3.7 Flash 2026-11 0.69
- 9 GPT-5.5 2026-11 0.71
- 10 Grok 4.6 2026-11 0.72
- 11 GPT-5.6 Luna 2026-11 0.74
- 12 GPT-5.1 2026-11 0.76
- 13 Claude Sonnet 5 2026-11 0.77
- 14 GLM-5.2 2026-11 0.79
- 15 GPT-5.6 Terra 2026-11 0.80
- 16 Grok 4.3 2026-11 0.84
- 17 mistral/ministral-14b-2512 2026-11 0.84
- 18 mistral/mistral-large-2512 2026-11 0.85
- 19
Qwen3.7-Max 2026-11 0.85
- 20
Voxtral Small 2026-11 0.90
- 21 mistralai/mistral-small-24b-instruct-2501 2026-11 0.93
- 22
Qwen3.5-9B 2026-11 0.94
- 23
Mistral NeMo 2026-11 0.96
- 24 mistral/ministral-3b-2512 2026-11 0.96
- 25 mistral/codestral-2508 2026-11 0.96
- 26 mistral/ministral-8b-2512 2026-11 0.97
- 27 mistral/mistral-small-2603 2026-11 1.01
- 28 gpt-oss-20b 2026-11 1.17
- 29 mistral/mistral-medium-2604 2026-11 1.78
- 30 qwen/qwen-2.5-7b-instruct 2026-11 2.16
- 31 meta-llama/llama-3.1-8b-instruct 2026-11 2.23
- 32
Gemma 3 4B 2026-11 3.50
Source: Official Guesswork (The Aggregate) leaderboard
- 1 GPT-6 Astra 2026-11 0.56
- 2 GPT-6.1 Sol 2026-11 0.56
- 3 Claude Opus 5.5 2026-11 0.57
- 4 Claude Fable 5.1 2026-11 0.60
- 5 Claude Sonnet 5.5 2026-11 0.64
- 6 Claude Opus 5 2026-11 0.65
- 7 Claude Opus 4.8 2026-11 0.68
- 8
Gemini 3.7 Flash 2026-11 0.69
- 9 GPT-5.5 2026-11 0.71
- 10 Grok 4.6 2026-11 0.72
- 11 GPT-5.6 Luna 2026-11 0.74
- 12 GPT-5.1 2026-11 0.76
- 13 Claude Sonnet 5 2026-11 0.77
- 14 GLM-5.2 2026-11 0.79
- 15 GPT-5.6 Terra 2026-11 0.80
- 16 Grok 4.3 2026-11 0.84
- 17
Qwen3.7-Max 2026-11 0.85
- 18
Voxtral Small 2026-11 0.90
- 19
Qwen3.5-9B 2026-11 0.94
- 20
Mistral NeMo 2026-11 0.96
- 21 gpt-oss-20b 2026-11 1.17
- 22
Gemma 3 4B 2026-11 3.50
Source: Official Guesswork (The Aggregate) leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 0.56 0.4 to 0.7 | 2026-11 | Sep 2026 | Official leaderboard |
| 2 | GPT-6.1 Sol | 0.56 0.4 to 0.7 | 2026-11 | Sep 2026 | Official leaderboard |
| 3 | Claude Opus 5.5 | 0.57 0.5 to 0.7 | 2026-11 | Sep 2026 | Official leaderboard |
| 4 | Claude Fable 5.1 | 0.60 0.5 to 0.8 | 2026-11 | Sep 2026 | Official leaderboard |
| 5 | Claude Sonnet 5.5 | 0.64 0.5 to 0.8 | 2026-11 | Sep 2026 | Official leaderboard |
| 6 | Claude Opus 5 | 0.65 0.5 to 0.8 | 2026-11 | Jul 2026 | Official leaderboard |
| 7 | Claude Opus 4.8 | 0.68 0.5 to 0.8 | 2026-11 | May 2026 | Official leaderboard |
| 8 | | 0.69 ±0.2 | 2026-11 | Aug 2026 | Official leaderboard |
| 9 | GPT-5.5 | 0.71 ±0.1 | 2026-11 | Apr 2026 | Official leaderboard |
| 10 | Grok 4.6 | 0.72 0.6 to 0.9 | 2026-11 | Aug 2026 | Official leaderboard |
| 11 | GPT-5.6 Luna | 0.74 0.6 to 0.9 | 2026-11 | Jul 2026 | Official leaderboard |
| 12 | GPT-5.1 | 0.76 ±0.1 | 2026-11 | Nov 2025 | Official leaderboard |
| 13 | Claude Sonnet 5 | 0.77 ±0.2 | 2026-11 | Jun 2026 | Official leaderboard |
| 14 | GLM-5.2 | 0.79 ±0.2 | 2026-11 | Jun 2026 | Official leaderboard |
| 15 | GPT-5.6 Terra | 0.80 ±0.2 | 2026-11 | Jul 2026 | Official leaderboard |
| 16 | Grok 4.3 | 0.84 ±0.2 | 2026-11 | Apr 2026 | Official leaderboard |
| 17 | mistral/ministral-14b-2512 | 0.84 ±0.2 | 2026-11 | Official leaderboard | |
| 18 | mistral/mistral-large-2512 | 0.85 0.7 to 1 | 2026-11 | Official leaderboard | |
| 19 | | 0.85 ±0.2 | 2026-11 | May 2026 | Official leaderboard |
| 20 | | 0.90 ±0.2 | 2026-11 | Jul 2025 | Official leaderboard |
| 21 | mistralai/mistral-small-24b-instruct-2501 | 0.93 0.7 to 1.2 | 2026-11 | Official leaderboard | |
| 22 | | 0.94 0.7 to 1.1 | 2026-11 | Feb 2026 | Official leaderboard |
| 23 | | 0.96 0.8 to 1.2 | 2026-11 | Jul 2024 | Official leaderboard |
| 24 | mistral/ministral-3b-2512 | 0.96 ±0.2 | 2026-11 | Official leaderboard | |
| 25 | mistral/codestral-2508 | 0.96 0.7 to 1.2 | 2026-11 | Official leaderboard | |
| 26 | mistral/ministral-8b-2512 | 0.97 0.8 to 1.2 | 2026-11 | Official leaderboard | |
| 27 | mistral/mistral-small-2603 | 1.01 0.8 to 1.2 | 2026-11 | Official leaderboard | |
| 28 | gpt-oss-20b | 1.17 1 to 1.4 | 2026-11 | Aug 2025 | Official leaderboard |
| 29 | mistral/mistral-medium-2604 | 1.78 0.7 to 3.8 | 2026-11 | Official leaderboard | |
| 30 | qwen/qwen-2.5-7b-instruct | 2.16 1 to 4.3 | 2026-11 | Official leaderboard | |
| 31 | meta-llama/llama-3.1-8b-instruct | 2.23 1.1 to 4.4 | 2026-11 | Official leaderboard | |
| 32 | | 3.50 1.8 to 5.9 | 2026-11 | Mar 2025 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 0.56 0.4 to 0.7 | 2026-11 | Sep 2026 | Official leaderboard |
| 2 | GPT-6.1 Sol | 0.56 0.4 to 0.7 | 2026-11 | Sep 2026 | Official leaderboard |
| 3 | Claude Opus 5.5 | 0.57 0.5 to 0.7 | 2026-11 | Sep 2026 | Official leaderboard |
| 4 | Claude Fable 5.1 | 0.60 0.5 to 0.8 | 2026-11 | Sep 2026 | Official leaderboard |
| 5 | Claude Sonnet 5.5 | 0.64 0.5 to 0.8 | 2026-11 | Sep 2026 | Official leaderboard |
| 6 | Claude Opus 5 | 0.65 0.5 to 0.8 | 2026-11 | Jul 2026 | Official leaderboard |
| 7 | Claude Opus 4.8 | 0.68 0.5 to 0.8 | 2026-11 | May 2026 | Official leaderboard |
| 8 | | 0.69 ±0.2 | 2026-11 | Aug 2026 | Official leaderboard |
| 9 | GPT-5.5 | 0.71 ±0.1 | 2026-11 | Apr 2026 | Official leaderboard |
| 10 | Grok 4.6 | 0.72 0.6 to 0.9 | 2026-11 | Aug 2026 | Official leaderboard |
| 11 | GPT-5.6 Luna | 0.74 0.6 to 0.9 | 2026-11 | Jul 2026 | Official leaderboard |
| 12 | GPT-5.1 | 0.76 ±0.1 | 2026-11 | Nov 2025 | Official leaderboard |
| 13 | Claude Sonnet 5 | 0.77 ±0.2 | 2026-11 | Jun 2026 | Official leaderboard |
| 14 | GLM-5.2 | 0.79 ±0.2 | 2026-11 | Jun 2026 | Official leaderboard |
| 15 | GPT-5.6 Terra | 0.80 ±0.2 | 2026-11 | Jul 2026 | Official leaderboard |
| 16 | Grok 4.3 | 0.84 ±0.2 | 2026-11 | Apr 2026 | Official leaderboard |
| 17 | | 0.85 ±0.2 | 2026-11 | May 2026 | Official leaderboard |
| 18 | | 0.90 ±0.2 | 2026-11 | Jul 2025 | Official leaderboard |
| 19 | | 0.94 0.7 to 1.1 | 2026-11 | Feb 2026 | Official leaderboard |
| 20 | | 0.96 0.8 to 1.2 | 2026-11 | Jul 2024 | Official leaderboard |
| 21 | gpt-oss-20b | 1.17 1 to 1.4 | 2026-11 | Aug 2025 | Official leaderboard |
| 22 | | 3.50 1.8 to 5.9 | 2026-11 | Mar 2025 | Official leaderboard |
4 models have held number one on the official leaderboard since its release in June 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Guesswork (The Aggregate) leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Guesswork (The Aggregate) leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Forecasting
- ForecastBench In use Models give probabilities for 500 auto-generated questions per round about future events, drawn from prediction markets and time-series datasets. Forecasts are scored with difficulty-adjusted Brier scores once the questions resolve. GPT-5.5 0.11
- Prophet Arena In use Models and agents forecast open Kalshi prediction-market events and are scored once the events resolve. The live board ranks a difficulty-adjusted Arena score and also reports calibration error and market return. Claude Opus 5.5 86.2
- AGI-Pilled Bench Not in model cards Models forecast when AI will reach milestones that already happened in 2026. The score is the median years after 2026 across the forecast tasks. Claude Fable 5.2 6.50
- Dutch Book Bench Not in model cards Models assign probabilities to related events in separate conversations. The grader checks whether inconsistent probabilities let a bettor guarantee a profit.
Gemini 3.8 Flash 89.2%
- Echo General AI Prediction Leaderboard Not in model cards Models forecast unresolved events drawn from prediction markets, synthesized news questions and expert-written questions. Forecasts made at aligned times are compared in pairwise battles, and an Elo fit ranks the models.
DeepSeek-V4-Pro 1,018
- SynthBench Not in model cards Models answer survey questions. The index compares their answer distributions with human responses across four datasets, using random answers and human agreement as reference points.
Qwen3.8 Flash 32.2
Data audit
9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (32 entries).
- Pass Models scored 22 models we track, plus 10 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
- Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on theaggregate.ai: 22 rows for models we track and 10 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.