tensor.news
Integrity IndexModelsCompareLabsPapersMethodologyAbout
tensor.news

© 2026

Evidence

  • Integrity Index
  • Model Claim Ledger
  • Compare

Entities

  • Models
  • Benchmarks
  • Labs
  • Papers

Method

  • Methodology
  • About
  • Privacy

Machine

  • Feed (Atom)
  • llms.txt
  • llms-full.txt
  • Sitemap

tensor.news grades benchmarks and tags model claims by evidence status. Every fact carries a source record and provenance. Scores are framed as task performance under a disclosed harness, never as deployed capability.

← Integrity Index

GBAEval

GBAEval

Rank #11 of 51 · 14 models scored · top score 74.47

AINTEGRITY 98 / 100

unknown

Strongest on discrimination, weakest on saturation headroom. Caveat: the public test set leaves contamination on the table.

consistent harnesspublic test set

Headroom to ceiling

25.5 headroomtop 74.5ceiling 100

Score distribution

median 6.7Claude Fable 5 74.503978

State of the art over time

0397874.520262026

Integrity breakdown

Weighted composite. Each signal is computed from the source-backed leaderboard below.

Discrimination30%100

Does it still separate models?

Saturation headroom30%95

How far from ceiling / clustered at the top?

Contamination resistance15%100

Public vs held-out; training-leak risk.

Harness comparability15%100

Apples-to-apples, or mixed / vendor-optimized?

Freshness10%100

How old is the benchmark?

Leaderboard

#ModelScoreEvidenceMeasured
1Claude Fable 574.47unverified2026-06-09
2Claude Opus 4.870.9unverified2026-05-28
3GPT-5.553.22unverified2026-04-23
4Claude Sonnet 4.648.76unverified2026-02-17
5Claude Opus 4.644.12unverified2026-02-05
6Claude Opus 4.743.81unverified2026-04-16
7GPT-5.431.6unverified2026-03-05
8Gemini 3.5 Flash6.7unverified2026-05-19
9Kimi K2.60.86unverified2026-04-20
10Gemini 3.1 Pro0.85unverified2026-02-19
11Qwen3.7-Max0.41unverified2026-05-19
12GLM-5.20.02unverified2026-06-16
13MiniMax-M2.70unverified2026-03-18
14GLM-5.10unverified2026-04-07

At a glance

Models scored
14
Top model
Claude Fable 5
Top score
74.47
Score spread
74.47
Headroom
25.53

Benchmark context

Task type
unknown
Metric
normalized performance in Epoch CSV, rendered as accuracy (%)
Score ceiling
100
Human baseline
unknown
Test-set privacy
unknown
Construction
unknown
Key assumptions
unknown
Limitations
unknown
Contamination history
unknown
Harness notes
Epoch CSV reports model, model version, performance, optimized flag, score source, benchmark release date, and model date.
Authors
unknown
Released
unknown
License
CC BY 4.0
Source
epoch.ai/data/eci_benchmarks.csv

Provenance

14 source records · scores from epoch_benchmarks. Every fact on this page is evidence-linked.

Follow the record

Integrity neighbors

  • CadEvalA · 98
  • CursorBenchA · 98
  • FrontierMath-Tiers-1-3-v2-PrivateA · 98
  • GDPvalA · 98
  • FrontierMath-Tier-4-2025-07-01-PrivateA · 93
  • CritPtA · 92

Top models here

  • Claude Fable 574.47
  • Claude Opus 4.870.9
  • GPT-5.553.22
  • Claude Sonnet 4.648.76
  • Claude Opus 4.644.12

Head-to-head

  • Claude Fable 5 vs Claude Opus 4.8
  • Claude Fable 5 vs GPT-5.5
  • Claude Opus 4.8 vs GPT-5.5