Surface Evolver Bench
Integrity rank #23 of 65 · 24 models scored · top score 95 · Claude Fable 5
unknown
Strongest on discrimination, weakest on contamination resistance. Caveat: the public test set does not rule out training-data contamination.
Reported scores — protocols may differ. How we compare
| # | Model | Score | Evidence | Measured |
|---|---|---|---|---|
| 1 | Claude Fable 5 | 95 | unverifiedT1 | 2026-06-09 |
| 2 | Kimi K3 | 95 | unverifiedT1 | 2026-07-16 |
| 3 | GPT-5.6 Sol | 93.12 | unverifiedT1 | 2026-07-09 |
| 4 | GPT-5.5 | 88.12 | unverifiedT1 | 2026-04-23 |
| 5 | Claude Opus 4.8 | 87.5 | unverifiedT1 | 2026-05-28 |
| 6 | GPT-5.6 Terra | 83.75 | unverifiedT1 | 2026-07-09 |
| 7 | Gemini 3.8 Flash | 76.88 | unverifiedT1 | 2026-09-02 |
| 8 | Grok 4.5 | 74.38 | unverifiedT1 | 2026-07-08 |
| 9 | GPT-5.6 Luna | 61.88 | unverifiedT1 | 2026-07-09 |
| 10 | Claude Sonnet 5 | 60 | unverifiedT1 | 2026-06-30 |
| 11 | Gemini 3.5 Flash | 58.13 | unverifiedT1 | 2026-05-19 |
| 12 | GLM-5.2 | 55.62 | unverifiedT1 | 2026-06-16 |
| 13 | MiniMax-M3 | 55 | unverifiedT1 | 2026-06-01 |
| 14 | Muse Spark 1.1 | 52.5 | unverifiedT1 | 2026-07-09 |
| 15 | GLM-5.3-Flash | 52.5 | unverifiedT1 | 2026-08-20 |
| 16 | Kimi K2.7 Code | 48.75 | unverifiedT1 | 2026-06-12 |
| 17 | DeepSeek V4.1 Flash | 46.25 | unverifiedT1 | 2026-09-09 |
| 18 | Qwen 3.8 27B | 45 | unverifiedT1 | 2026-08-14 |
| 19 | Qwen 3.6 35B-A3B | 44.38 | unverifiedT1 | 2026-04-14 |
| 20 | DeepSeek-V4-Pro | 40 | unverifiedT1 | 2026-04-24 |
| 21 | Gemma 4 31B IT | 30.62 | unverifiedT1 | 2026-04-02 |
| 22 | Mistral Large 4 | 28.12 | unverifiedT1 | 2026-10-06 |
| 23 | Mistral Medium 3.5 | 26.88 | unverifiedT1 | 2026-04-28 |
| 24 | gpt-oss-120b | 25 | unverifiedT1 | 2025-08-05 |
Continue from this leaderboard into the tightest head-to-head reads.
Weighted composite. Each dimension opens to the source-backed sub-signals it is computed from.
Claims drawn from cited facts, not live model generation.
The recorded metadata does not specify what this benchmark measures.
1 cited fact
This benchmark has scores from 24 tracked models, with a recorded score range spanning 70.0.
2 cited facts
Its Benchmark Integrity Index score is 89, with grade A and rank 23 out of 65 tracked benchmarks.
4 cited facts
It is flagged as saturated. The top recorded score is 95.0, with 5.0 points of headroom. The computed top-score cluster contains 3 models.
4 cited facts
The harness classification is consistent harness. Test-set privacy is recorded as unknown. The recorded contamination-window ratio is 0.5.
3 cited facts
Surface Evolver Bench: Surface Evolver Bench as reported in Epoch AI's Capabilities Index CSV.
Claude Fable 5 leads Surface Evolver Bench at 95. The full leaderboard above lists every recorded measurement, not just the headline number.
24 models have recorded scores on Surface Evolver Bench, spanning a score spread of 70.
tensor.news grades Surface Evolver Bench A for integrity (score 89/100), ranking #23 of 65 benchmarks we assess across discrimination, saturation, contamination resistance, harness comparability, and freshness.
Yes — top scores are clustering near the ceiling (saturation ratio 0.13), so Surface Evolver Bench no longer separates leading models well. Treat small gaps at the top with caution.
Its test set is unknown, so contamination risk is on the table: a high score may partly reflect training-data overlap rather than capability.
Scores are reported under a consistent harness, so comparisons on Surface Evolver Bench are reasonably apples-to-apples.
Every Surface Evolver Bench measurement is source-backed and tagged reproduced, self-reported, or unverified; the underlying record cites epoch.ai/data/eci_benchmarks.csv.