Vals AI
This reference reads 30 independent leaderboards · 28 model pages · 1 benchmark page from Vals AI. Each source below links to the original publication and the pages it supports.
- Website
- vals.ai
- Pages read
- 59
- Published figures
- 2,172
- Last read
- 17 October 2026
Pages read from this site
Original publications, their figure counts, and where they are used in this reference.
- —figures
Claude Fable 5.1 — Vals AI model page
www.vals.ai/models/anthropic_claude-fable-5-1Used on these pages
- —figures
Claude Opus 5 — Vals AI model page
www.vals.ai/models/anthropic_claude-opus-5Used on these pages
- —figures
Claude Opus 5.5 — Vals AI model page
www.vals.ai/models/anthropic_claude-opus-5-5Used on these pages
- —figures
Claude Sonnet 5 — Vals AI model page
www.vals.ai/models/anthropic_claude-sonnet-5Used on these pages
- —figures
Claude Sonnet 5.5 — Vals AI model page
www.vals.ai/models/anthropic_claude-sonnet-5-5Used on these pages
- 8figures
CUA-bench
www.vals.ai/benchmarks/cua_benchUsed on these pages
- 43figures
CyberBench v1.1
www.vals.ai/benchmarks/cyberUsed on these pages
- —figures
DeepSeek V4 Pro — Vals AI model page
www.vals.ai/models/deepseek_deepseek-v4-pro-0813Used on these pages
- —figures
DeepSeek V4.1 Flash — Vals AI model page
www.vals.ai/models/deepseek_deepseek-v4.1-flashUsed on these pages
- 69figures
EMB
www.vals.ai/benchmarks/embUsed on these pages
- 73figures
Finance Agent (v2)
www.vals.ai/benchmarks/fabv2Used on these pages
- —figures
Gemini 3.1 Pro — Vals AI model page
www.vals.ai/models/google_gemini-3.1-pro-previewUsed on these pages
- —figures
Gemini 3.8 Flash — Vals AI model page
www.vals.ai/models/google_gemini-3.8-flashUsed on these pages
- —figures
Gemini 4 Argon — Vals AI model results
www.vals.ai/models/google_gemini-4-argonUsed on these pages
- —figures
GLM 5.3 — Vals AI model page
www.vals.ai/models/zai_glm-5.3Used on these pages
- 138figures
GPQA Diamond
www.vals.ai/benchmarks/gpqaUsed on these pages
- 106figures
GPT-5.4 — Vals AI published results
www.vals.ai/benchmarks/vibe-codeUsed on these pages
- —figures
GPT-5.6 Luna — Vals AI model page
www.vals.ai/models/openai_gpt-5.6-lunaUsed on these pages
- —figures
GPT-5.6 Sol — Vals AI model page
www.vals.ai/models/openai_gpt-5.6-solUsed on these pages
- 71figures
GPT-5.6 Terra — Vals AI published results
www.vals.ai/benchmarks/code-migrationUsed on these pages
- —figures
GPT-6 Astra — Vals AI model page
www.vals.ai/models/openai_gpt-6-astraUsed on these pages
- 21figures
GPT-6 Luna — Vals AI published results
www.vals.ai/benchmarks/biomysterybenchUsed on these pages
Show 2 more linked pages
- —figures
GPT-6 Sol — Vals AI model page
www.vals.ai/models/openai_gpt-6-solUsed on these pages
- —figures
GPT-6.1 Sol — Vals AI model page
www.vals.ai/models/openai_gpt-6.1-solUsed on these pages
- —figures
Grok 4.7 — Vals AI model page
www.vals.ai/models/grok_grok-4.7Used on these pages
- 73figures
Harvey's Legal Agent Benchmark
www.vals.ai/benchmarks/hlabUsed on these pages
- —figures
Hunyuan Hy4 Preview — Vals AI model page
www.vals.ai/models/tencent_hy4-previewUsed on these pages
- —figures
Inkling — Vals AI model page
www.vals.ai/models/thinkingmachines_inklingUsed on these pages
- 38figures
IOI
www.vals.ai/benchmarks/ioiUsed on these pages
- —figures
Kimi K3 — Vals AI model page
www.vals.ai/models/kimi_kimi-k3Used on these pages
- 72figures
Legal Research Bench
www.vals.ai/benchmarks/legal_researchUsed on these pages
- 149figures
LegalBench
www.vals.ai/benchmarks/legal_benchUsed on these pages
- 143figures
LiveCodeBench
www.vals.ai/benchmarks/lcbUsed on these pages
- 104figures
MedCode
www.vals.ai/benchmarks/medcodeUsed on these pages
- 106figures
MedScribe
www.vals.ai/benchmarks/medscribeUsed on these pages
- —figures
MiMo V2.6 Pro — Vals AI model page
www.vals.ai/models/xiaomi_mimo-v2.6-proUsed on these pages
- —figures
MiniMax M3 — Vals AI model page
www.vals.ai/models/minimax_MiniMax-M3Used on these pages
- —figures
Mistral Medium 3.5 — Vals AI model page
www.vals.ai/models/mistralai_mistral-medium-3.5Used on these pages
- 138figures
MMLU Pro
www.vals.ai/benchmarks/mmlu_proUsed on these pages
- 93figures
MMMU Pro
www.vals.ai/benchmarks/mmmuUsed on these pages
- —figures
Muse Spark 1.3 Max — Vals AI model page
www.vals.ai/models/meta_muse_spark_1_3_maxUsed on these pages
- 21figures
MysteryMechanism
www.vals.ai/benchmarks/mysterymechanismUsed on these pages
- 54figures
ProgramBench
www.vals.ai/benchmarks/programbenchUsed on these pages
- —figures
ProgramBench
www.vals.ai/benchmarks/programbench-hidden-evalUsed on these pages
- 46figures
ProofBench v1.1
www.vals.ai/benchmarks/proof_benchUsed on these pages
- 45figures
Public Benefits Bench v1.1
www.vals.ai/benchmarks/public-benefits-benchUsed on these pages
- —figures
Qwen3.8 Max — Vals AI model page
www.vals.ai/models/alibaba_qwen3.8-maxUsed on these pages
- 90figures
SAGE
www.vals.ai/benchmarks/sageUsed on these pages
- 35figures
SkillsBench
www.vals.ai/benchmarks/skillsbenchUsed on these pages
- 16figures
SRE Bench
www.vals.ai/benchmarks/srebenchUsed on these pages
- 88figures
SWE-bench (Verified)
www.vals.ai/benchmarks/swebenchUsed on these pages
- 64figures
Tax Agent Bench
www.vals.ai/benchmarks/tax_agent_benchUsed on these pages
- 75figures
Terminal-Bench 2.1
www.vals.ai/benchmarks/terminal-bench-2-1Used on these pages
- 42figures
Terminal-Bench 4.0 — Vals AI
www.vals.ai/benchmarks/terminal-bench-4Used on these pages
- 34figures
Terminal-Bench Science 0.1 — Vals AI
www.vals.ai/benchmarks/terminal-bench-scienceUsed on these pages
- 41figures
Vals Index
www.vals.ai/benchmarks/vals_indexUsed on these pages
- 33figures
Vals Multimodal Index
www.vals.ai/benchmarks/vals_multimodal_indexUsed on these pages
- 23figures
Vals RSI Index
www.vals.ai/benchmarks/rsi_indexUsed on these pages
- 20figures
Vibe Code Bench 1–100
www.vals.ai/benchmarks/vcb-1-100Used on these pages