Other · model
Pokee-Isaac 28B benchmark scores
As of 2026-10-07, Pokee-Isaac 28B (Other) has measured scores on 3 benchmarks and estimated scores on 12 more.
| Benchmark | Score | Source |
|---|---|---|
| GDPval-AA | 13.3% | estimated ± 5.8 pp, medium confidence |
| AA-LCR | 69.8% | estimated ± 4.5 pp, medium confidence |
| Terminal-Bench 2.1 | 65.1% | measured |
| τ²-bench results | 90.7% | estimated ± 14.1 pp, low confidence |
| BFCL v4 | 70.9% | measured |
| τ³-bench results | 66.2% | measured |
| WideResearch | 71.4% | estimated ± 12.4 pp, low confidence |
| Terminal-Bench 3.0 | 6.5% | estimated ± 9.1 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 56.2% | estimated ± 7.4 pp, medium confidence |
| AA Terminal-Bench 2.1 | 60.6% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 2.0% | estimated ± 8.9 pp, medium confidence |
| Claw-Eval | 64.4% | estimated ± 2.3 pp, medium confidence |
| DeepPlanning | 16.9% | estimated ± 8.3 pp, low confidence |
| MCP-Tasks | 63.1% | estimated ± 3.6 pp, medium confidence |
| Toolathlon | 31.8% | estimated ± 6.0 pp, low confidence |