33.7%
AA Intelligence Index v4.1
Models / Other
KAT Coder · Released 2026-03-27
AA Intelligence Index 33.7. Listed on Artificial Analysis with API pricing $0.3/$1.2 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
65average across 4 tested families
Where KAT Coder Pro V2 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | Agentic | #29/ 148 | 70 | Artificial Analysis | 2026-07-28 |
| AA time to first token | Performance | #37/ 149 | Artificial Analysis | 2026-07-28 | |
| AA output speed | Performance | #39/ 149 | Artificial Analysis | 2026-07-28 | |
| AA-LCR | Long context | #61/ 143 | 66 | Artificial Analysis | 2026-07-28 |
| IFBench | Reasoning | #65/ 121 | 67 | Artificial Analysis | 2026-07-28 |
| GPQA Diamond | Reasoning | #74/ 149 | 86 | Artificial Analysis | 2026-07-28 |
| Artificial Analysis Intelligence Index | Reasoning | #94/ 147 | 34 | Artificial Analysis | 2026-07-28 |
| Humanity's Last Exam | Reasoning | #104/ 144 | 16 | Artificial Analysis | 2026-07-28 |
| SciCode | Coding | #110/ 144 | 38 | Artificial Analysis | 2026-07-28 |
| τ³-Bench Banking | Agentic | #135/ 143 | 6 | Artificial Analysis | 2026-07-28 |
The three highest-scoring carded models in each capability family. Where KAT Coder Pro V2 shows up, it's highlighted.
Benchmark rows added to the public ledger for KAT Coder Pro V2 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 66% | Artificial Analysis | 4 |
| AA output speed | Performance | 101 t/s | Artificial Analysis | 4 |
| AA time to first token | Performance | 1.45s | Artificial Analysis | 4 |
| Artificial Analysis Intelligence Index | Reasoning | 33.7% | Artificial Analysis | 4 |
| GPQA Diamond | Reasoning | 85.5% | Artificial Analysis | 4 |
| Humanity's Last Exam | Reasoning | 16% | Artificial Analysis | 4 |
| IFBench | Reasoning | 66.67% | Artificial Analysis | 4 |
| SciCode | Coding | 38.3% | Artificial Analysis | 4 |
| τ³-Bench Banking | Agentic | 5.77% | Artificial Analysis | 4 |
| Terminal-Bench | Agentic | 70.04% | Artificial Analysis | 4 |
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Hover or tab any dot for name, score, and input price.
Every catalog benchmark for KAT Coder Pro V2. Scores link to the original source; gaps mean no public row exists yet.
10 of 32 catalog benchmarks have a sourced row for KAT Coder Pro V2.
33.7%
AA Intelligence Index v4.1
85.5%
GPQA Diamond (AA run)
16%
HLE (AA run)
66.67%
IFBench (AA run)
38.3%
SciCode (AA run)
70.04%
Terminal-Bench v2.1 (AA run)
5.77%
τ³-Bench Banking (AA run)
66%
AA-LCR (AA run)
101 t/s
Median output tokens/s (1k prompt, default provider)
1.45s
Median time to first token (1k prompt, default provider)