K2 Horizon 375B A23B
- Input
- —
- Output
- —
- Speed
- 124tok/s
- Context
- 524Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: K2 Horizon 375B A23B. Price = AA median host price.
Rankings
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.
- Hardware
- 8× H200 141GB
- FP8 weights
- Throughput
- ~22,644 tok/s
- many requests batched
- Price
- $0.17–1.38 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Ultra 512GB (int4, ~73 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (375B params, 23B active per token) + 40% KV-cache headroom ≈ 525 GB
- 8× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~22,644 output tok/s aggregate at batch 814 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~162,622 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#13 of 21 (estimated)~73.3%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #12Flint74.2%
- ~#13K2 Horizon 375B A23BEstimated73.3%
- #13Claude Haiku 4.573.3%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#20 of 24 (estimated)~53.0%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #18Gemini 3.5 Flash-Lite54.2%
- ~#20K2 Horizon 375B A23BEstimated53.0%
- #20Nemotron 3.5 Super VL51.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~47.5%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38K2 Horizon 375B A23BEstimated47.5%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#45 of 1011.5%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #43MiniMax-M32.0%
- #45K2 Horizon 375B A23B1.5%
- #46Gemini 3.5 Flash-Lite1.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#15 of 28 (estimated)~67.8%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15K2 Horizon 375B A23BEstimated67.8%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#69 of 11842.9%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #68Nex-N2-Pro43.3%
- #69K2 Horizon 375B A23B42.9%
- #70Ling-3.0-flash-Fin42.4%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#24 of 26 (estimated)~32.4
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #23Gemini 3.8 Flash33.3
- ~#24K2 Horizon 375B A23BEstimated32.4
- #24GPT-6 Luna31.1
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#48 of 19287.3%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #47GPT-5.4 mini87.5%
- #48K2 Horizon 375B A23B87.3%
- #49Inkling87.2%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#53 of 19832.0%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #52Inkling Small33.3%
- #53K2 Horizon 375B A23B32.0%
- #54Inkling31.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#7 of 34 (estimated)~94.3%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #6Muse Glimmer94.7%
- ~#7K2 Horizon 375B A23BEstimated94.3%
- #7Nova 2.0 Lite94.3%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#28 of 120 (estimated)~81.8%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #26Nemotron 3 Ultra83.3%
- ~#28K2 Horizon 375B A23BEstimated81.8%
- #28Nex-N2-Pro81.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#9 of 15 (estimated)~74.4%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #8GPT-5.578.7%
- ~#9K2 Horizon 375B A23BEstimated74.4%
- #9Gemini 3.5 Flash-Lite74.0%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#14 of 22 (estimated)~78.0%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #13Nex-N2.5-Mini83.4%
- ~#14K2 Horizon 375B A23BEstimated78.0%
- #14Nemotron 3.5 Super VL78.0%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#29 of 911361 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #28Qwen3.8 27B1419
- #29K2 Horizon 375B A23B1361
- #30GPT-5.51336
artificialanalysis.ai · 2026-10-10