Open Weights & Proprietary

Models

Model Name Release Date Image
Claude Opus 4.7 4/16/2026
Muse Spark 4/8/2026
Gemma 4 31B IT 4/2/2026
Qwen 3.6 Plus 4/2/2026
GLM 5.1 4/1/2026
Trinity Large Thinking 4/1/2026
GPT 5.4 Mini 3/17/2026
GPT 5.4 Nano 3/17/2026
MiniMax-M2.7 3/9/2026
Grok 4.20 (Reasoning) 3/5/2026
GPT 5.4 3/3/2026
Gemini 3.1 Flash Lite Preview 2/24/2026
GPT 5.3 Codex 2/23/2026
Qwen 3.5 Flash 2/19/2026
Gemini 3.1 Pro Preview (02/26) 2/17/2026
Claude Sonnet 4.6 2/16/2026
Qwen 3.5 Plus 2/12/2026
MiniMax-M2.5 2/12/2026
MiniMax-M2.5 2/11/2026
GLM 5 2/5/2026
Claude Opus 4.6 (Nonthinking) 2/5/2026
Claude Opus 4.6 (Thinking) 1/26/2026
Kimi K2.5 1/23/2026
Qwen 3 Max Thinking 12/23/2025
MiniMax-M2.1 12/22/2025
GLM 4.7 12/17/2025
Gemini 3 Flash (12/25) 12/17/2025
MiMo V2 Flash 12/11/2025
GPT 5.2 12/11/2025
GPT 5.2 Codex 12/11/2025

Kimi K2 Thinking

Release Date: 11/6/2025

Accuracy (Vals Index)

  • 50.97% ± 1.99

Latency (Vals Index)

  • 726.14s

Cost/Test (Vals Index)

  • $0.16

Context Window

  • 256k

Max Output Tokens

  • 32k

Input Modality

  • Hyperparameter settings

Default Provider

  • Moonshot AI

Some benchmarks may use different provider and parameters. Please refer to the benchmark page for more information.

Temperature

  • 0.6

Top P

  • Default

Top K

  • Default

Max Output Tokens

  • 32,000

Show rankings only among open weight models

Benchmarks

Benchmark Accuracy Rankings
Vals Index -123.04% ± 1.99 64/ 40
CaseLaw (v2) -187.22% ± 1.82 155/ 47
CorpFin -201.62% ± 0.96 297/ 97
Finance Agent (v1.1) -140.96% ± 2.61 83/ 45
TaxEval (v2) -315.75% ± 0.88 368/ 104
AIME -427.21% ± 1.33 396/ 96
GPQA -443.12% ± 2.18 432/ 99
LiveCodeBench -399.54% ± 1.16 356/ 103
LegalBench -565.98% ± 0.46 589/ 116
MedQA -725.54% ± 0.24 612/ 95
MMLU Pro -702.08% ± 0.40 521/ 97
SWE-bench -574.06% ± 2.19 108/ 41
Terminal-Bench 2.0 -387.96% ± 5.15 293/ 52

Proprietary Benchmarks

Contact us to get access

Academic Benchmarks