> model race

Who's winning the model race?

A twice-daily Boostor snapshot for frontier model performance, coding strength, agentic readiness, tool support, and cost efficiency.

tooling feed live, benchmark key neededrefresh every 12h/api/model-race

leader

models

68%

data health

Aug 22

updated

> leaderboard

Composite race score

Sort by any column, filter by provider, and refresh live data. Artificial Analysis drives the benchmark score when configured. Without that key, the page clearly falls back to OpenRouter's live tooling and economics feed.

JSON feed

sort

provider

DeepSeek V4 Flash 0731

tooling proxy

DeepSeek · 1M ctx

95.1

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

98.5

source

MiMo-V2.5

tooling proxy

Xiaomi · 1M ctx

92.4

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

97.7

source

Hy3

tooling proxy

Tencent · 262K ctx

91.5

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

96.4

source

GPT-5.6 Luna

tooling proxy

OpenAI · 1.1M ctx

90.5

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

93.4

source

DeepSeek V4 Flash 0423

tooling proxy

DeepSeek · 1M ctx

90.1

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

98.9

source

GLM 5.2

tooling proxy

Z.ai · 1M ctx

84.4

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

86.8

source

Ox Alpha

tooling proxy

Ox Alpha · 1M ctx

83.1

intel

n/a

code

n/a

agent

n/a

tools

66.7

value

100

source

DeepSeek V4 Pro 0423

tooling proxy

DeepSeek · 1M ctx

83.1

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

94.3

source

MiniMax M3

tooling proxy

MiniMax · 1M ctx

81.6

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

93.1

source

Claude Opus 5

tooling proxy

Claude Opus 5 · 1M ctx

79.9

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

67.4

source

Nemotron 3 Ultra (free)

tooling proxy

NVIDIA · 1M ctx

79.6

intel

n/a

code

n/a

agent

n/a

tools

value

100

source

Gemini 3.7 Flash

tooling proxy

Google · 1M ctx

78.7

intel

n/a

code

n/a

agent

n/a

tools

83.3

value

90.7

source

> subcharts

Tooling and value signals

Benchmarks pick winners. Builders also need to know which model can call tools, return structured output, fit the repo, and stay affordable.

Rank my stack

Tool-calling readiness

OpenRouter-supported parameters, filtered to agent-builder relevant capabilities.

subchart

model	tools	structured outputs	reasoning	response format	web search	score
DeepSeek V4 Flash 0731 DeepSeek

model

tools

structured outputs

reasoning

response format

web search

score

DeepSeek V4 Flash 0731

DeepSeek

> sources

Benchmark coverage map

The page separates structured live feeds from tracked benchmark sources. That keeps the chart useful without pretending every leaderboard exposes a clean API.

Who's winning the model race?

Composite race score

DeepSeek V4 Flash 0731

MiMo-V2.5

Hy3

GPT-5.6 Luna

DeepSeek V4 Flash 0423

GLM 5.2

Ox Alpha

DeepSeek V4 Pro 0423

MiniMax M3

Claude Opus 5

Nemotron 3 Ultra (free)

Gemini 3.7 Flash

Tooling and value signals

Tool-calling readiness

Benchmark coverage map

DeepSeek V4 Flash 0731

tooling feed live, benchmark key needed

Price, score, context