Calibration
Decision Index Arts → Artificial Analysis Decision Index v1.0
Artificial Analysis Decision Index v1.0 is estimated from Decision Index Arts with a Michaelis–Menten curve fitted on 11 models measured on both: y = 2.0000·x / (1.31403 + x), R² = 0.84, cross-validated error 3.2 pp. It is used for 72 estimates.
| Estimated model | Decision Index Arts | Artificial Analysis Decision Index v1.0 | Source |
|---|---|---|---|
| mammoth-1 | 62.7% | 64.6% | estimated ± 3.2 pp, medium confidence |
| Perplexity Decider v1.3 27B | 55.7% | 59.5% | estimated ± 3.2 pp, high confidence |
| Blink v0.3 26B-A4B (NVFP4) | 52.3% | 56.9% | estimated ± 3.2 pp, high confidence |
| Torchcast Decision 27B | 52.2% | 56.9% | estimated ± 3.2 pp, high confidence |
| Surogate Rune 26B-A4B v3 | 52.0% | 56.7% | estimated ± 3.2 pp, high confidence |
| GEV-26B-Decide | 48.6% | 54.0% | estimated ± 3.2 pp, high confidence |
| Xor 1.2 | 48.1% | 53.6% | estimated ± 3.2 pp, high confidence |
| Bespoke Nimble 9B v3 | 47.2% | 52.9% | estimated ± 3.2 pp, high confidence |
| Eikos-27B | 47.1% | 52.8% | estimated ± 3.2 pp, high confidence |
| JEV-27B | 46.9% | 52.6% | estimated ± 3.2 pp, high confidence |
| Perplexity Decider Flash v1.3 4B | 46.9% | 52.6% | estimated ± 3.2 pp, high confidence |
| vLLM-SR Decision 2.0 Vega 27B | 45.6% | 51.5% | estimated ± 3.2 pp, high confidence |
| simple-jev · Qwen3.8-27B | 45.3% | 51.3% | estimated ± 3.2 pp, high confidence |
| JADE | 45.2% | 51.2% | estimated ± 3.2 pp, high confidence |
| Kev 27B | 45.1% | 51.1% | estimated ± 3.2 pp, high confidence |
| Quyet-1.0-Large | 45.1% | 51.1% | estimated ± 3.2 pp, high confidence |
| deck31b (Gemma 4 31B) | 44.3% | 50.4% | estimated ± 3.2 pp, high confidence |
| Decider chat · Gemma-4-31B | 44.3% | 50.4% | estimated ± 3.2 pp, high confidence |
| decider-35b-a3b | 42.9% | 49.2% | estimated ± 3.2 pp, high confidence |
| Decider chat · Qwen3.6-27B | 42.9% | 49.2% | estimated ± 3.2 pp, high confidence |
| JPT-35B-A3B | 41.4% | 47.9% | estimated ± 3.2 pp, high confidence |
| JoshuaSP diffusiongemma (open-jev) | 40.9% | 47.5% | estimated ± 3.2 pp, high confidence |
| decisio 0.4.0 (Qwen3.6-35B-A3B) | 40.2% | 46.9% | estimated ± 3.2 pp, high confidence |
| lev | 39.4% | 46.1% | estimated ± 3.2 pp, high confidence |
| decisio 0.4.0 (Gemma 4 12B) | 38.7% | 45.5% | estimated ± 3.2 pp, high confidence |
| Lev1 3.7B | 38.7% | 45.5% | estimated ± 3.2 pp, high confidence |
| ezjev 4B s2 | 37.8% | 44.7% | estimated ± 3.2 pp, high confidence |
| Jevfire | 37.6% | 44.5% | estimated ± 3.2 pp, medium confidence |
| vLLM-SR Decision 2.0 Lux 9B | 37.6% | 44.5% | estimated ± 3.2 pp, medium confidence |
| djev | 37.4% | 44.3% | estimated ± 3.2 pp, medium confidence |
| Hopper 12B (trained) | 37.3% | 44.2% | estimated ± 3.2 pp, medium confidence |
| razorback16 openjev diffusiongemma (NVFP4, vLLM) | 35.9% | 42.9% | estimated ± 3.2 pp, medium confidence |
| Ryotide Qwen v0.3.1 | 35.7% | 42.7% | estimated ± 3.2 pp, medium confidence |
| JevK5 9B v0.3.3 | 35.1% | 42.2% | estimated ± 3.2 pp, medium confidence |
| Jobe | 35.1% | 42.2% | estimated ± 3.2 pp, medium confidence |
| Winnow-12B Q8 | 35.1% | 42.2% | estimated ± 3.2 pp, medium confidence |
| JEV-9B | 34.6% | 41.7% | estimated ± 3.2 pp, medium confidence |
| Decider 4B | 34.5% | 41.6% | estimated ± 3.2 pp, medium confidence |
| Bespoke Nimble 9B v2 | 34.2% | 41.3% | estimated ± 3.2 pp, medium confidence |
| Hopper (G) 1.2 | 34.0% | 41.1% | estimated ± 3.2 pp, medium confidence |
| JevK5 v0.3 | 33.5% | 40.6% | estimated ± 3.2 pp, medium confidence |
| JPT-9B | 33.2% | 40.3% | estimated ± 3.2 pp, medium confidence |
| mmastrac diffusiongemma (vLLM PR 57250) | 33.2% | 40.3% | estimated ± 3.2 pp, medium confidence |
| SemIf | 33.0% | 40.1% | estimated ± 3.2 pp, medium confidence |
| Intern-Decision-4B | 32.9% | 40.0% | estimated ± 3.2 pp, medium confidence |
| openvons | 32.7% | 39.9% | estimated ± 3.2 pp, medium confidence |
| mini-jev | 31.9% | 39.1% | estimated ± 3.2 pp, medium confidence |
| vLLM-SR Decision 2.0 Nox 4B | 31.9% | 39.1% | estimated ± 3.2 pp, medium confidence |
| Jev-Omni | 31.9% | 39.1% | estimated ± 3.2 pp, medium confidence |
| Kas 4B | 31.6% | 38.8% | estimated ± 3.2 pp, medium confidence |
| Solomon v1.1 | 30.7% | 37.9% | estimated ± 3.2 pp, medium confidence |
| JPT-4B | 30.6% | 37.8% | estimated ± 3.2 pp, medium confidence |
| Sieve 9B | 29.7% | 36.9% | estimated ± 3.2 pp, medium confidence |
| Gevva E4B | 28.3% | 35.4% | estimated ± 3.2 pp, medium confidence |
| Winnow-E4B | 28.2% | 35.3% | estimated ± 3.2 pp, medium confidence |
| Tev1-4B-experimental | 27.3% | 34.4% | estimated ± 3.2 pp, medium confidence |
| Intelif Qwen3-4B | 27.2% | 34.3% | estimated ± 3.2 pp, medium confidence |
| Bekko System One v0 400M | 24.6% | 31.5% | estimated ± 3.2 pp, medium confidence |
| decider-2b | 24.4% | 31.3% | estimated ± 3.2 pp, medium confidence |
| Sieve 2B | 23.6% | 30.5% | estimated ± 3.2 pp, medium confidence |
| Kev 4B r10 | 23.0% | 29.8% | estimated ± 3.2 pp, medium confidence |
| metask-jev-4b | 22.2% | 28.9% | estimated ± 3.2 pp, medium confidence |
| Intern-Decision-2B | 21.4% | 28.0% | estimated ± 3.2 pp, medium confidence |
| Kev 9B v2 | 21.3% | 27.9% | estimated ± 3.2 pp, medium confidence |
| open-jev (pngwn) | 20.3% | 26.8% | estimated ± 3.2 pp, medium confidence |
| this-that 1.2 | 19.1% | 25.4% | estimated ± 3.2 pp, medium confidence |
| Jevstral 8B | 17.6% | 23.6% | estimated ± 3.2 pp, medium confidence |
| Kodiak v0.2 1B (accuracy) | 17.3% | 23.3% | estimated ± 3.2 pp, medium confidence |
| Bekko System One v0 68M | 16.9% | 22.8% | estimated ± 3.2 pp, medium confidence |
| vLLM-SR Decision 2.0 Sol 2B | 16.3% | 22.1% | estimated ± 3.2 pp, medium confidence |
| EXAONE-4.0-1.2B-JEV v0.3 | 16.2% | 22.0% | estimated ± 3.2 pp, medium confidence |
| NeoHorse-Jev-4B | 15.5% | 21.1% | estimated ± 3.2 pp, medium confidence |
Fitted on
| Model | Decision Index Arts | Artificial Analysis Decision Index v1.0 |
|---|---|---|
| Clef | 44.7% | 48.6% |
| Clef-Flash | 39.3% | 45.8% |
| Clef-Omni | 37.8% | 44.3% |
| Drex Max | 56.0% | 63.7% |
| Drex v1.5 | 50.1% | 50.7% |
| Drex v2.0 | 55.2% | 57.9% |
| elephant-1 | 56.7% | 64.7% |
| GLiDE v1.2 | 62.3% | 65.0% |
| Jev 1.14 | 47.7% | 57.1% |
| Perplexity Decider Flash v1.2 4B | 45.0% | 50.2% |
| Perplexity Decider v1.2 27B | 56.4% | 56.2% |