Open Weights & Proprietary

All Companies

Release date Models

4/16/2026

Claude Opus 4.7

4/8/2026

Muse Spark

4/2/2026

Gemma 4 31B IT

4/2/2026

Qwen 3.6 Plus

4/1/2026

GLM 5.1

4/1/2026

Trinity Large Thinking

3/17/2026

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

Claude Opus 4.6 (Thinking)

Compare Models

Claude Opus 4.6 (Thinking)

Release Date: 2/5/2026

Accuracy (Vals Index)

65.88%
± 1.94

Latency (Vals Index)

334.54s

Cost/Test (Vals Index)

$0.89

Context Window

200k

Max Output Tokens

128k

Input Modality

Hyperparameter settings

• Default Provider: Anthropic

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

Benchmarks

Accuracy

Rankings

• Vals Index](/content/benchmarks/vals_index/index.html) -72.44%
  ± 1.94
  81/ 40

• Vals Multimodal Index](/content/benchmarks/vals_multimodal_index/index.html) -91.32%
  ± 1.53
  62/ 28

• CaseLaw (v2) -108.87%
  ± 0.37
  98/ 47

• CorpFin -143.38%
  ± 0.93
  298/ 97

• Finance Agent (v1.1) -153.66%
  ± 2.78
  150/ 45

• MedCode -148.08%
  ± 2.09
  172/ 51

• MedScribe -302.01%
  ± 1.94
  219/ 51

• MortgageTax -276.66%
  ± 0.91
  319/ 69

• ProofBench -230.45%
  ± 5.03
  121/ 24

• SAGE -269.93%
  ± 3.34
  279/ 49

• TaxEval (v2) -447.11%
  ± 0.83
  699/ 104

• Vibe Code Bench -351.96%
  ± 4.68
  158/ 26

• AIME -700.67%
  ± 0.64
  733/ 96

• GPQA -727.91%
  ± 1.19
  846/ 99

• LiveCodeBench -758.96%
  ± 1.02
  901/ 103

• LegalBench -840.74%
  ± 0.37
  1191/ 116

• MedQA -1030.59%
  ± 0.19
  992/ 95

• MMLU Pro -1051.55%
  ± 0.45
  1195/ 97

• MMMU Pro -1078.09%
  ± 0.88
  786/ 66

• SWE-bench -1092.00%
  ± 1.85
  558/ 41

• Terminal-Bench 2.0 -884.16%
  ± 5.25
  733/ 52

Contact us

• Or send us an email at contact@vals.ai

Proprietary Benchmarks

Academic Benchmarks

Read about our methodology.