K2 Horizon 375B A23B · Intelligence Index v5.0 ↗
1 more reported result
30.50 index · K2 Horizon 375B A23B · Intelligence Index v4.3.2 · Artificial Analysis ↗
Kimi / MODEL EVIDENCE
K2 Horizon 375B A23B
22 benchmarks · 26 observations · 20 sources · released 2026-09-03
Scores at a glance
22 benchmarks · large dot: K2 Horizon 375B A23B; small dots: closest models where reported
AA-Briefcase v1.1 ↗1293.36 Elo
K2 Horizon 375B A23B · AA-Briefcase v1.1 · overall Elo ↗
AutomationBench-AA ↗37.21%
K2 Horizon 375B A23B · AutomationBench-AA · guardrail-gated objective score ↗
GDP.pdf ↗7.40%
K2 Horizon 375B A23B · GDP.pdf · all-pass ↗
Terminal-Bench 4.0 ↗1.52%
K2 Horizon 375B A23B · Terminal-Bench 4.0 · AA harness ↗
K2 Horizon 375B A23B · Terminal-Bench-Science 0.1 · AA harness ↗
FrontierCode 2.0 ↗11.85%
K2 Horizon 375B A23B · FrontierCode 2.0 · AA implementation ↗
K2 Horizon 375B A23B · CritPt v2 · hard subset · AA implementation ↗
HLE-Diamond ↗10.20%
K2 Horizon 375B A23B · HLE-Diamond · AA implementation ↗
AA-Omniscience v1.1 ↗-5.00 index
K2 Horizon 375B A23B · AA-Omniscience v1.1 · error-penalized index ↗
1 more reported result
-2.97 index · K2 Horizon 375B A23B · AA-Omniscience · error-penalized score · Artificial Analysis ↗
K2 Horizon 375B A23B · AA-Omniscience v1.1 · accuracy ↗
1 more reported result
18.18% · K2 Horizon 375B A23B · AA-Omniscience · accuracy · Artificial Analysis ↗
K2 Horizon 375B A23B · AA-Omniscience v1.1 · hallucination rate, lower is better ↗
1 more reported result
25.85% · K2 Horizon 375B A23B · AA-Omniscience · hallucination rate, lower is better · Artificial Analysis ↗
GDPval-AA v2.1 ↗1358.46 Elo
K2 Horizon 375B A23B · GDPval-AA v2.1 · Elo ↗
FrontierCode 1.1 ↗32.10%
K2 Horizon 375B A23B · FrontierCode 1.1 · AA implementation ↗
AA-LCR v1.1 ↗80.00%
K2 Horizon 375B A23B · AA-LCR v1.1 ↗
SciCode ↗42.94%
K2 Horizon 375B A23B · SciCode · AA implementation ↗
Humanity’s Last Exam ↗31.97%
K2 Horizon 375B A23B · Humanity’s Last Exam · AA implementation ↗
GPQA Diamond ↗87.27%
K2 Horizon 375B A23B · GPQA Diamond · AA implementation ↗
MLCR-AA ↗12.22%
K2 Horizon 375B A23B · MLCR-AA · overall ↗
τ³-Banking ↗34.23%
K2 Horizon 375B A23B · τ³-Banking ↗
Terminal-Bench 2.1 ↗71.91%
K2 Horizon 375B A23B · Terminal-Bench 2.1 ↗
CritPt ↗4.57%
K2 Horizon 375B A23B · CritPt · original ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Nemotron 3.5 Super VL →NVIDIA
18 of 21 shared benchmark comparisons
21 of 21 shared benchmark comparisons
Qwen3.8 27B →Qwen
21 of 21 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- AA-Briefcase v1.1: Agentic Knowledge Work Benchmark | Artificial Analysis ↗
- Artificial Analysis Intelligence Index v5.0 — Artificial Analysis ↗
- AA-LCR v1.1: Long Context Reasoning Benchmark | Artificial Analysis ↗
- AutomationBench-AA: Agentic SaaS Workflow Benchmark | Artificial Analysis ↗
- CritPt Benchmark | Artificial Analysis ↗
- CritPt v2 — Hard Subset — Artificial Analysis ↗
- FrontierCode 1.1 Benchmark | Artificial Analysis ↗
- FrontierCode 2.0 Benchmark — Artificial Analysis ↗
- GDP.pdf Benchmark | Artificial Analysis ↗
- GDPval-AA v2.1 Benchmark | Artificial Analysis ↗
- GPQA Diamond Benchmark | Artificial Analysis ↗
- HLE-Diamond Benchmark — Artificial Analysis ↗
- Humanity's Last Exam Benchmark | Artificial Analysis ↗
- MLCR-AA: Medical Long Context Reasoning Benchmark | Artificial Analysis ↗
- AA-Omniscience v1.1: Knowledge and Hallucination Benchmark — Artificial Analysis ↗
- SciCode Benchmark | Artificial Analysis ↗
- 𝜏³-Banking Benchmark | Artificial Analysis ↗
- Terminal-Bench-Science 0.1 Benchmark | Artificial Analysis ↗
- Terminal-Bench 2.1 Benchmark | Artificial Analysis ↗
- Terminal-Bench 4.0 Benchmark | Artificial Analysis ↗
Names used in source tables
K2 Horizon 375B A23B