Benchmark Almanac

Prediction Arena

Claude Opus 4.6 $138,945 leads since February 2026
Not in model cards

Agents research events and trade contracts on Kalshi and Polymarket. The leaderboard ranks accounts by cash plus the market value of open positions.

The researchers published Kalshi standings for six models trading real money and reported four more models trading on paper. WIRED covered the experiment in its AI Lab newsletter.

Released
January 2026
Kind
Real-world events
Level
University
Scored
Settled by events
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Multi-agent
Items from
Live play or votes
Refresh
Live
Run by
A host
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
March 2026
Scores refreshed
November 20th, 2026
10
Entries on its own leaderboard, 9 models we track

Claude Opus 4.6 leads with $138,945 among models released by March 2026 Claude Opus 4.6 leads with $138,945 among models released by March 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. Every run is in the next chart. 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 March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Opus 4.6 Polymarket $138,945
  2. 2 Gemini 3.1 Pro Polymarket $28,114
  3. 3 GLM-5 Kalshi $16,942
  4. 4 GPT-5.4 Polymarket $15,412
  5. 5 Grok 4.1 Fast Polymarket $10,004
  6. 6 GLM-4.7 Polymarket $9,983
  7. 7 Claude Opus 4.5 Polymarket $9,888
  8. 8 GPT-5.2 Polymarket $9,823
  9. 9 mystery-model-alpha Polymarket $9,794
  10. 10 Gemini 3 Pro Polymarket $9,770

Source: Official Prediction Arena leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 4.6 $138,945 Polymarket Feb 2026 Official leaderboard
2 Gemini 3.1 Pro $28,114 Polymarket Feb 2026 Official leaderboard
3 GLM-5 $16,942 Kalshi Feb 2026 Official leaderboard
4 GPT-5.4 $15,412 Polymarket Mar 2026 Official leaderboard
5 Grok 4.1 Fast $10,004 Polymarket Nov 2025 Official leaderboard
6 GLM-4.7 $9,983 Polymarket Dec 2025 Official leaderboard
7 Claude Opus 4.5 $9,888 Polymarket Nov 2025 Official leaderboard
8 GPT-5.2 $9,823 Polymarket Dec 2025 Official leaderboard
9 mystery-model-alpha $9,794 Polymarket Official leaderboard
10 Gemini 3 Pro $9,770 Polymarket Nov 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 4.6 $138,945 Polymarket Feb 2026 Official leaderboard
2 Gemini 3.1 Pro $28,114 Polymarket Feb 2026 Official leaderboard
3 GLM-5 $16,942 Kalshi Feb 2026 Official leaderboard
4 GPT-5.4 $15,412 Polymarket Mar 2026 Official leaderboard
5 Grok 4.1 Fast $10,004 Polymarket Nov 2025 Official leaderboard
6 GLM-4.7 $9,983 Polymarket Dec 2025 Official leaderboard
7 Claude Opus 4.5 $9,888 Polymarket Nov 2025 Official leaderboard
8 GPT-5.2 $9,823 Polymarket Dec 2025 Official leaderboard
9 Gemini 3 Pro $9,770 Polymarket Nov 2025 Official leaderboard

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Opus 4.6
Kalshi Polymarket
$138,945
Gemini 3.1 Pro
Kalshi Polymarket
$28,114
GLM-5
Polymarket
$16,942
GPT-5.4
Kalshi
$15,412
Grok 4.1 Fast
Kalshi
$10,004
GLM-4.7
Kalshi
$9,983
Claude Opus 4.5
Kalshi
$9,888
GPT-5.2
Kalshi
$9,823
Gemini 3 Pro
Kalshi
$9,770

Source: Official Prediction Arena leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Opus 4.6 Polymarket $138,945
Gemini 3.1 Pro Polymarket $28,114
Gemini 3.1 Pro Kalshi $17,426
GLM-5 Kalshi $16,942
GPT-5.4 Polymarket $15,412
Claude Opus 4.6 Kalshi $14,073
GPT-5.4 Kalshi $10,122
Grok 4.1 Fast Polymarket $10,004
GLM-4.7 Polymarket $9,983
Claude Opus 4.5 Polymarket $9,888
GPT-5.2 Polymarket $9,823
Gemini 3 Pro Polymarket $9,770
GLM-4.7 Kalshi $8,460
Claude Opus 4.5 Kalshi $7,338
GPT-5.2 Kalshi $7,322
GLM-5 Polymarket $7,053
Grok 4.1 Fast Kalshi $6,925
Gemini 3 Pro Kalshi $6,903

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Opus 4.6
Kalshi Polymarket
$138,945
Gemini 3.1 Pro
Kalshi Polymarket
$28,114
GLM-5
Polymarket
$16,942
GPT-5.4
Kalshi
$15,412
Grok 4.1 Fast
Kalshi
$10,004
GLM-4.7
Kalshi
$9,983
Claude Opus 4.5
Kalshi
$9,888
GPT-5.2
Kalshi
$9,823
Gemini 3 Pro
Kalshi
$9,770

Source: Official Prediction Arena leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Opus 4.6 Polymarket $138,945
Gemini 3.1 Pro Polymarket $28,114
Gemini 3.1 Pro Kalshi $17,426
GLM-5 Kalshi $16,942
GPT-5.4 Polymarket $15,412
Claude Opus 4.6 Kalshi $14,073
GPT-5.4 Kalshi $10,122
Grok 4.1 Fast Polymarket $10,004
GLM-4.7 Polymarket $9,983
Claude Opus 4.5 Polymarket $9,888
GPT-5.2 Polymarket $9,823
Gemini 3 Pro Polymarket $9,770
GLM-4.7 Kalshi $8,460
Claude Opus 4.5 Kalshi $7,338
GPT-5.2 Kalshi $7,322
GLM-5 Polymarket $7,053
Grok 4.1 Fast Kalshi $6,925
Gemini 3 Pro Kalshi $6,903

2 models have held number one on the official leaderboard since its release in January 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

xAI Anthropic
Own leaderboard Not tested since Mar 2026
Claude Opus 4.6 $138,945

Source: Official Prediction Arena leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
$0 $50,000 $100,000 $150,000 2026 $0 $50,000 $100,000 $150,000 2026

Source: Official Prediction Arena 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

All 47 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
  • Guesswork (The Aggregate) Not in model cards 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. GPT-6 Astra 0.56
  • 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

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 8 months ago, in March 2026, for GPT-5.4. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 9 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 8 months ago, in March 2026, for GPT-5.4.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
  • Note Headroom Scored as US dollars, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on predictionarena.ai: 18 rows for models we track and 1 other entry 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.

How we check