FrontierCode

Measures whether maintainers would merge code changes on real-world software tasks. Pass rates at the listed reasoning effort and cost per rollout from FrontierCode.

1. 1Claude Opus 5.5[high]58.9%@ $1.09/rollout
2. 2GPT-6 Astra[high]56.2%@ $3.01/rollout
3. 3Claude Fable 5.1[high]55.1%@ $5.27/rollout
4. 4GPT-6.1 Sol[high]53.2%@ $0.50/rollout
5. 5Grok 4.7[high]53.1%@ $6.65/rollout

Pricing

Per-million-token pricing and prompt-cache rates for every model behind the Revolt endpoint.

FrontierOpenAIClaudeSpaceX AI

GPT-6 Astra

Context

1.05M

Max output

128K

Input type

file, text, image

Output type

text

Data retention

no

Input

$10

Output

$50

Cache read

$1

Cache write

$12.50

GPT-6.1 Sol

Context

1.05M

Max output

128K

Input type

file, text, image

Output type

text

Data retention

no

Input

$2

Output

$10

Cache read

$0.10

Cache write

$2.50

Claude Fable 5.1

Context

1M

Max output

128K

Input type

file, text, image

Output type

text

Data retention

30 days

Input

$10

Output

$50

Cache read

$0.25

Cache write (5m)

$12.50

Cache write (1h)

$20

Claude Opus 5.5

Context

1M

Max output

128K

Input type

file, text, image

Output type

text

Data retention

30 days

Input

$4

Output

$20

Cache read

$0.20

Cache write (5m)

$5

Cache write (1h)

$8

Grok 4.7

Context

500K

Max output

64K

Input type

file, text, image

Output type

text

Data retention

no

Input

$2

Output

$6

Cache read

$0.50

Cache write

Free