Devforth
Cost-performance analysis

Which Model Is Best for Coding?

A cost-performance leaderboard of the models coding agents run on - benchmark scores, real token-mix pricing, latency, and decoding speed.

Models used by coding agents

Sort by:
  • Anthropic
    Claude Opus 5.5 Anthropic
    #1
    DF Score 96.1
    Avg task cost $1.19
    Latency —
    Context window 1M
  • Anthropic
    Claude Sonnet 5.5 Anthropic
    #2
    DF Score 92.8
    Avg task cost —
    Latency 446.00s
    Context window 1M
  • Google
    Gemini 4 Argon Google
    #3
    DF Score 89.6
    Avg task cost $0.211
    Latency 44.70s
    Context window 1M
  • Anthropic
    Claude Fable 5.1 Anthropic
    #4
    DF Score 87.3
    Avg task cost $2.73
    Latency 210.79s
    Context window 1M
  • OpenAI
    GPT-6 Astra OpenAI
    #5
    DF Score 84.8
    Avg task cost $1.15
    Latency —
    Context window 1M
  • OpenAI
    GPT-6.1 Sol OpenAI
    #6
    DF Score 82.5
    Avg task cost $0.181
    Latency 301.70s
    Context window 1.05M
  • OpenAI
    GPT-6 Sol OpenAI
    #7
    DF Score 78.4
    Avg task cost $0.201
    Latency 136.12s
    Context window 872k
  • Anthropic
    Claude Fable 5 Anthropic
    #8
    DF Score 78.2
    Avg task cost $2.36
    Latency 239.01s
    Context window 1M
  • Anthropic
    Claude Opus 5 Anthropic
    #9
    DF Score 76.8
    Avg task cost $0.821
    Latency 56.78s
    Context window 1M
  • OpenAI
    GPT-5.6 Sol OpenAI
    #10
    DF Score 76.5
    Avg task cost $0.350
    Latency —
    Context window 1.05M
  • OpenAI
    GPT-5.6 Terra OpenAI
    #11
    DF Score 71.0
    Avg task cost $0.234
    Latency —
    Context window 1.05M
  • Google
    Gemini 3.8 Flash Google
    #12
    DF Score 65.6
    Avg task cost $0.135
    Latency 14.66s
    Context window 1M
  • Anthropic
    Claude Haiku 5.5 Anthropic
    #13
    DF Score 64.2
    Avg task cost —
    Latency 336.90s
    Context window 1M
  • OpenAI
    GPT-5.4 OpenAI
    #14
    DF Score 63.3
    Avg task cost $0.254
    Latency 113.80s
    Context window 1M
  • OpenAI
    GPT-5.5 OpenAI
    #15
    DF Score 60.9
    Avg task cost $0.490
    Latency 118.46s
    Context window 1.05M
  • Anthropic
    Claude Opus 4.7 Anthropic
    #16
    DF Score 60.7
    Avg task cost $1.58
    Latency —
    Context window 1M
  • OpenAI
    GPT-6 Luna OpenAI
    #17
    DF Score 59.7
    Avg task cost $0.00843
    Latency 93.68s
    Context window 1.05M
  • Anthropic
    Claude Opus 4.8 Anthropic
    #18
    DF Score 59.4
    Avg task cost $1.16
    Latency 30.05s
    Context window 1M
  • OpenAI
    GPT-5.6 Luna OpenAI
    #19
    DF Score 58.6
    Avg task cost $0.0301
    Latency —
    Context window 1.05M
  • Anthropic
    Claude Sonnet 5 Anthropic
    #20
    DF Score 55.6
    Avg task cost $0.969
    Latency 144.37s
    Context window 1M
  • Anthropic
    Claude Opus 4.6 Anthropic
    #21
    DF Score 51.6
    Avg task cost $0.581
    Latency —
    Context window 1M
  • Google
    Gemini 3.1 Pro (Preview) Google
    #22
    DF Score 51.3
    Avg task cost $0.783
    Latency 25.74s
    Context window 1M
  • Anthropic
    Claude Opus 4.5 Anthropic
    #23
    DF Score 48.1
    Avg task cost —
    Latency 15.04s
    Context window 200k
  • Google
    Gemini 3.5 Flash Google
    #24
    DF Score 46.9
    Avg task cost $0.620
    Latency 20.59s
    Context window 1M
  • Google
    Gemini 3 Flash (Preview) Google
    #25
    DF Score 46.3
    Avg task cost —
    Latency 7.60s
    Context window 1M
  • Anthropic
    Claude Sonnet 4.6 Anthropic
    #26
    DF Score 40.7
    Avg task cost —
    Latency 1.16s
    Context window 1M
  • OpenAI
    GPT-5.4 mini OpenAI
    #27
    DF Score 38.8
    Avg task cost $0.183
    Latency 11.87s
    Context window 400k
  • Kimi-K2.7-Code Moonshot AI
    #28
    DF Score 37.5
    Avg task cost —
    Latency 2.92s
    Context window 256k
  • OpenAI
    GPT-5.4 nano OpenAI
    #29
    DF Score 28.4
    Avg task cost —
    Latency 4.74s
    Context window 400k
  • Anthropic
    Claude Sonnet 4.5 Anthropic
    #30
    DF Score 26.8
    Avg task cost —
    Latency 1.36s
    Context window 1M
  • Anthropic
    Claude Haiku 4.5 Anthropic
    #31
    DF Score 21.5
    Avg task cost $0.159
    Latency 0.81s
    Context window 200k
  • Google
    Gemini 2.5 Pro Google
    #32
    DF Score 20.1
    Avg task cost —
    Latency 22.54s
    Context window 1M
  • OpenAI
    GPT-5 mini OpenAI
    #33
    DF Score 19.1
    Avg task cost —
    Latency 85.30s
    Context window 400k
  • OpenAI
    GPT-OSS 120B OpenAI
    #34
    DF Score 0.0
    Avg task cost —
    Latency 0.94s
    Context window 131k
  • Raptor mini GitHub
    #35
    DF Score —
    Avg task cost —
    Latency —
    Context window 400k
  • MAI-Code-1-Flash Microsoft
    #36
    DF Score —
    Avg task cost —
    Latency —
    Context window
  • Anthropic
    Claude Opus 4.8 Fast Anthropic
    #37
    DF Score —
    Avg task cost —
    Latency —
    Context window 1M

Help us to detect updates in plans values

The prices and token mixes above are driven by real coding usage. Share yours via letmecode to allow us discover updates in plans values.

$ npx letmecode@latest

FAQ

The agent decision

Your model choice sets the budget. The agent sets the workflow.

Compare leading coding agents on the models they bundle, limits, and pricing to see which one turns your model choice into the best engineering results.

See the agent rankings Limits, models & cost

Something unclear or missing?

If any of the numbers or terms above don't add up, or you spotted something that looks off, tell us - we'll clarify and keep the data sharper for everyone.

Report inconsistency

Found it useful - share

Share this comparison with the world to give everyone the opportunity to make the right choice based on real numbers instead of marketing claims.