Leaderboard

Model rankings / 2026

Independent benchmark scores, divided by what this market actually charges.

450
Ranked models
24
With scores
8%
Average saving
Ability
Performance
Price
Per dollar
This market

Intelligence

The composite index across nine evaluations — the closest thing to a single answer to “how capable is this model”.

gpt-6-astra56.995% below list
claude-opus-5-559.195% below list
gpt-6.1-sol54.695% below list
Top 10
  1. 1claude-opus-5-5by Anthropic59.195% below list
  2. 2gpt-6-astraby OpenAI56.995% below list
  3. 3gpt-6.1-solby OpenAI54.695% below list
  4. 4claude-sonnet-5-5by Anthropic54.595% below list
  5. 5gpt-6.1-terraby OpenAI51.395% below list
  6. 6gemini-4-argonby Google50.495% below list
  7. 7claude-fable-5-1by Anthropic49.295% below list
  8. 8kimi-k3.1-proby Moonshot46.590% below list
  9. 9gpt-6-solby OpenAI44.295% below list
  10. 10claude-haiku-5-5by Anthropic36.595% below list

Each vendor's best, side by side

The strongest model each vendor brings to this ranking. Every axis is scaled to the best on the board, so the outer ring is always the leader.

No model has every axis measured yet.

Whose board is this

Tradable models per vendor, and the strongest score each one brings.

450models
Qwen
60 models13%33.7
OpenAI
44 models10%56.9
Google
32 models7%50.4
Mistral
24 models5%—
Recraft
15 models3%—
Microsoft
11 models2%—
xAI
11 models2%35.5
ByteDance Seed
10 models2%—
Z.ai
10 models2%31.7
InclusionAI
9 models2%—
MiniMax
9 models2%—
Tencent
9 models2%—
Amazon
8 models2%—
Anthropic
8 models2%59.1
Black Forest Labs
8 models2%—
Meta
8 models2%—
Meta Llama
8 models2%—
NVIDIA
8 models2%13.6
Cohere
7 models2%6.2
DeepSeek
7 models2%32.6
Perplexity
7 models2%—
ByteDance
6 models1%—
AionLabs
5 models1%—
Alibaba
5 models1%—
Fish Audio
5 models1%—
Moonshot
5 models1%46.5
Sentence Transformers
5 models1%—
Voyage AI
5 models1%—
Xiaomi
5 models1%—
HeyGen
4 models1%—
Krea
4 models1%—
NEX AGI
4 models1%—
Nous Research
4 models1%—
Sakana AI
4 models1%—
Sourceful
4 models1%—
TheDrummer
4 models1%—
BAAI
3 models1%—
Deepgram
3 models1%—
IBM Granite
3 models1%—
Inception
3 models1%—
intfloat
3 models1%—
KwaiPilot
3 models1%—
KwaiVGI
3 models1%—
Liquid AI
3 models1%—
Poolside
3 models1%—
Sao10K
3 models1%—
StepFun
3 models1%—
Upstage
3 models1%—
Arcee AI
2 models0%—
Inflection
2 models0%—
Morph
2 models0%—
Perceptron
2 models0%—
Reka
2 models0%—
Relace
2 models0%—
Runway
2 models0%—
thenlper
2 models0%—
Thinking Machines
2 models0%—
AI21
1 models0%—
AllenAI
1 models0%—
Anthracite
1 models0%—
Baidu
1 models0%—
Canopy Labs
1 models0%—
Cognitive Computations
1 models0%—
Deep Cogito
1 models0%—
Gryphe
1 models0%—
Hexgrad
1 models0%—
Mancer
1 models0%—
Meituan
1 models0%—
Sesame
1 models0%—
Undi95
1 models0%—
Writer
1 models0%—

Intelligence against price

Every model twice: where the vendor prices it, and where it trades here.

OpenAIAnthropicGoogleMoonshotxAI
$0.01$0.10$1$10$1000204060Intelligence indexBlended price · USD / 1M tokensclaude-fable-5-1claude-opus-5-5kimi-k3.1-progpt-6.1-solgpt-6.1-terra
Vendor list pricePrice on AsaleValue frontier

Every model

One entry per model: catalog ids naming the same model collapse to whichever does best on the ranking shown.

Open the market

Scores last pulled Nov 4, 2026.