Task ranking

Best LLM for Coding

Claude Opus 5.5 ranks first for Coding as of October 20, 2026.[1][2] It scores 64.85% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#1 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks. Claude Sonnet 5.5 scores within two points, so read the top two as close rather than as a measured gap. Claude Sonnet 5.5 is the next-ranked alternative. It scores 91.37% on LiveBench Coding (#1 of 59), an objective evaluation of code generation and completion.

About this recommendation

Updated
Evidence through
Sources
10
Revision
v123

Decision audit

Why this result

Inspect the inputs and the computed order behind the recommendation.

Models screened

24

live candidates

Evaluation feeds

7

task-weighted

Winner coverage

64%

intended feed weight

Largest provider share

3 of 8

Anthropic

Established source breadth. 4 citation families and 2 practitioner families provide attributed capability reports; 0 cautionary threads retained. The largest citation family contributes 30%.

Anthropic: Claude Opus 5.5 leads the measured task comparison with 4 independent evaluation families. Community volume, release age and usage popularity add no ranking points. The leading scores are close under this policy.

Sources evaluated

These are the weights used in scoring. Missing measurements are omitted from each model’s average. A feed with no result for any model released in the last 60 days is stale and does not score until it catches up.

winner: Claude Opus 5.5
Evaluation feedWeightWinner resultField measured
LMArena WebDevObserved 2026-10-19 · evaluation date not supplied · max effort
31%
#123/24
LiveBench Coding (2026-06-25)Observed 2026-10-18 · evaluation date not supplied · claude-opus-5-5-max-effortfailing; last successful check 2026-10-18
28%
#217/24
SWE-rebenchstale
0%
no current result0/24
Design Arena CodingObserved 2026-10-20 · evaluation date not supplied · anthropic/claude-opus-5.5-20260921
24%
#121/24
Aider Polyglotstale
0%
no current result0/24
Terminal-Bench (4.0)Observed 2026-10-20 · evaluated 2026-10-06 · Claude Code; max effort · 95% interval ±3.11
17%
#110/24
SWE-bench Verifiedstale
0%
no current result0/24

Provider concentration

Each exact model is scored separately; provider identity is not a ranking input.

Anthropic38%
  • Anthropic3 models
  • OpenAI2 models
  • deepseek1 model
  • Google1 model
  • Meta1 model

Decision table

Every published model is shown in computed order. Practitioner sources are distinct community threads, not the citations repeated in the prose below.

  1. 01Claude Opus 5.598

    Anthropic · coverage 64%

    #1 Design Arena Coding · #1 LMArena WebDev

  2. 02Claude Sonnet 5.596

    Anthropic · coverage 64% · close score

    #1 LiveBench Coding · #2 Terminal-Bench

  3. 03Claude Fable 5.187

    Anthropic · coverage 64%

    #3 LiveBench Coding · #5 LMArena WebDev

  4. 04Muse Wonder85

    Meta · coverage 36%

    #2 Design Arena Coding · #13 LMArena WebDev

  5. 05Gemini 4 Argon84

    Google · coverage 36%

    #8 LMArena WebDev · #9 Design Arena Coding

  6. 06DeepSeek V4.1 Flash 101783

    deepseek · coverage 36%

    #8 Design Arena Coding · #10 LMArena WebDev

  7. 07GPT-6.1 Sol82

    OpenAI · coverage 64%

    #3 Terminal-Bench · #4 LMArena WebDev

  8. 08GPT-6 Astra80

    OpenAI · coverage 49%

    #2 LMArena WebDev · #3 Terminal-Bench

Task score averages the available, task-weighted measurements. Benchmark positions compare models matched to our catalog. Models measured by at least two independent evaluator families are considered first. Missing tests, practitioner report counts, popularity and release age add no points. Coverage describes evidence breadth, not a probability of correctness. Scores within two points are shown as close under this policy; this is not a statistical confidence interval. When the leading scores are that close, the model measured by more evaluator families ranks first.

  1. 01

    Claude Opus 5.5Anthropic · $4 in / $20 out per M tokens · 1M context

    Claude Opus 5.5 scores 64.85% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#1 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.

    Best when: Its strongest result for this task is on Terminal-Bench, which measures completing difficult repository and terminal tasks through an agent harness.
    Source 1
    “Within the 23 catalog models matched to this evaluation: Scores 64.85% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#1 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.”
    Terminal-BenchOpen original ↗
  2. 02

    Claude Sonnet 5.5Anthropic · $2 in / $10 out per M tokens · 1M context

    Claude Sonnet 5.5 scores 91.37% on LiveBench Coding (#1 of 59), an objective evaluation of code generation and completion.

    Best when: Its strongest result for this task is on LiveBench Coding, which measures code generation and completion.
    Source 2
    “Within the 59 catalog models matched to this evaluation: Scores 91.37% on LiveBench Coding (#1 of 59), an objective evaluation of code generation and completion.”
    LiveBench CodingOpen original ↗

    No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.

  3. 03

    Claude Fable 5.1Anthropic · $10 in / $50 out per M tokens · 1M context

    Claude Fable 5.1 scores 86.38% on LiveBench Coding (#3 of 59), an objective evaluation of code generation and completion.

    Best when: Its strongest result for this task is on LiveBench Coding, which measures code generation and completion.
    Source 4
    “Within the 59 catalog models matched to this evaluation: Scores 86.38% on LiveBench Coding (#3 of 59), an objective evaluation of code generation and completion.”
    LiveBench CodingOpen original ↗

    No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.

  4. 04

    Muse WonderMeta · $4 in / $20 out per M tokens · 1.0M context

    Ranks second in human preference for coding output quality on Design Arena while showing competitive performance on web development tasks.

    Best when: Select when human preference rankings indicate output quality, placing #2 of 117 on Design Arena coding category (Elo 1370).
    Source 5
    “Within the 117 catalog models matched to this evaluation: Ranks #2 of 117 on Design Arena's coding category (Elo 1370), based on blind human preference between generated coding results.”
    Design Arena codingOpen original ↗

    Watch out for

    • Expect lower web development specific performance, ranking #13 of 99 on LMArena WebDev (Elo 1652).
      Source 6
      “Within the 99 catalog models matched to this evaluation: Ranks #13 of 99 on LMArena's WebDev coding arena (Elo 1652), a leaderboard built from blind human preference votes on coding tasks.”
      LMArena WebDev (coding) arenaOpen original ↗
  5. 05

    Gemini 4 ArgonGoogle · $2 in / $10 out per M tokens · 1.0M context

    Mid-tier rankings across human preference arenas with competitive but not leading performance on coding-specific evaluations.

    Best when: Consider for general coding tasks, ranking #9 of 117 on Design Arena (Elo 1328) and #8 of 99 on LMArena WebDev (Elo 1678).
    Source 7
    “Within the 117 catalog models matched to this evaluation: Ranks #9 of 117 on Design Arena's coding category (Elo 1328), based on blind human preference between generated coding results.”
    Design Arena codingOpen original ↗
    Source 8
    “Within the 99 catalog models matched to this evaluation: Ranks #8 of 99 on LMArena's WebDev coding arena (Elo 1678), a leaderboard built from blind human preference votes on coding tasks.”
    LMArena WebDev (coding) arenaOpen original ↗

    No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.

  6. 06

    DeepSeek V4.1 Flash 1017deepseek · $0.30 in / $1.20 out per M tokens · 1.0M context · open-weight

    DeepSeek V4.1 Flash 1017 ranks #8 of 117 on Design Arena's coding category (Elo 1333), based on blind human preference between generated coding results.

    Best when: Its strongest result for this task is on Design Arena coding, which measures coding results preferred in blind head-to-head comparisons.
    Source 3
    “Within the 117 catalog models matched to this evaluation: Ranks #8 of 117 on Design Arena's coding category (Elo 1333), based on blind human preference between generated coding results.”
    Design Arena codingOpen original ↗

    No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.

  7. 07

    GPT-6.1 SolOpenAI · $2 in / $10 out per M tokens · 1.1M context

    GPT-6.1 Sol scores 58.18% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#3 of 23) at max reasoning effort, using Codex, measuring a model-and-agent configuration on reproducible terminal tasks.

    Best when: Its strongest result for this task is on Terminal-Bench, which measures completing difficult repository and terminal tasks through an agent harness.
    Source 9
    “Within the 23 catalog models matched to this evaluation: Scores 58.18% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#3 of 23) at max reasoning effort, using Codex, measuring a model-and-agent configuration on reproducible terminal tasks.”
    Terminal-BenchOpen original ↗

    No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.

  8. 08

    GPT-6 AstraOpenAI · $10 in / $50 out per M tokens · 1.1M context

    GPT-6 Astra ranks #2 of 99 on LMArena's WebDev coding arena (Elo 1774), a leaderboard built from blind human preference votes on coding tasks.

    Best when: Its strongest result for this task is on LMArena WebDev, which measures practical, real-world coding quality.
    Source 10
    “Within the 99 catalog models matched to this evaluation: Ranks #2 of 99 on LMArena's WebDev coding arena (Elo 1774), a leaderboard built from blind human preference votes on coding tasks.”
    LMArena WebDev (coding) arenaOpen original ↗

Freshness check

New models awaiting independent results

These recently released, tool-capable models are relevant to coding but do not yet have enough independent evidence to place confidently in the ranking above.

Frequently asked

What is the best model for Coding?
Claude Opus 5.5 ranks first as of October 20, 2026. Claude Opus 5.5 scores 64.85% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#1 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.[1]
What is the best alternative to Claude Opus 5.5?
Claude Sonnet 5.5 ranks second. Claude Sonnet 5.5 scores 91.37% on LiveBench Coding (#1 of 59), an objective evaluation of code generation and completion.[2]
Which open-weight model ranks highest for Coding?
DeepSeek V4.1 Flash 1017 is the highest-ranked open-weight model, at #6. DeepSeek V4.1 Flash 1017 ranks #8 of 117 on Design Arena's coding category (Elo 1333), based on blind human preference between generated coding results.[3]

Sources

  1. 1

    “Within the 23 catalog models matched to this evaluation: Scores 64.85% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#1 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.”

    Terminal-Bench · Benchmark · Oct 20, 2026
  2. 2

    “Within the 59 catalog models matched to this evaluation: Scores 91.37% on LiveBench Coding (#1 of 59), an objective evaluation of code generation and completion.”

    LiveBench Coding · Benchmark · Oct 18, 2026
  3. 3

    “Within the 117 catalog models matched to this evaluation: Ranks #8 of 117 on Design Arena's coding category (Elo 1333), based on blind human preference between generated coding results.”

    Design Arena coding · Benchmark · Oct 20, 2026
  4. 4

    “Within the 59 catalog models matched to this evaluation: Scores 86.38% on LiveBench Coding (#3 of 59), an objective evaluation of code generation and completion.”

    LiveBench Coding · Benchmark · Oct 18, 2026
  5. 5

    “Within the 117 catalog models matched to this evaluation: Ranks #2 of 117 on Design Arena's coding category (Elo 1370), based on blind human preference between generated coding results.”

    Design Arena coding · Benchmark · Oct 20, 2026
  6. 6

    “Within the 99 catalog models matched to this evaluation: Ranks #13 of 99 on LMArena's WebDev coding arena (Elo 1652), a leaderboard built from blind human preference votes on coding tasks.”

    LMArena WebDev (coding) arena · Benchmark · Oct 19, 2026
  7. 7

    “Within the 117 catalog models matched to this evaluation: Ranks #9 of 117 on Design Arena's coding category (Elo 1328), based on blind human preference between generated coding results.”

    Design Arena coding · Benchmark · Oct 20, 2026
  8. 8

    “Within the 99 catalog models matched to this evaluation: Ranks #8 of 99 on LMArena's WebDev coding arena (Elo 1678), a leaderboard built from blind human preference votes on coding tasks.”

    LMArena WebDev (coding) arena · Benchmark · Oct 19, 2026
  9. 9

    “Within the 23 catalog models matched to this evaluation: Scores 58.18% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#3 of 23) at max reasoning effort, using Codex, measuring a model-and-agent configuration on reproducible terminal tasks.”

    Terminal-Bench · Benchmark · Oct 20, 2026
  10. 10

    “Within the 99 catalog models matched to this evaluation: Ranks #2 of 99 on LMArena's WebDev coding arena (Elo 1774), a leaderboard built from blind human preference votes on coding tasks.”

    LMArena WebDev (coding) arena · Benchmark · Oct 19, 2026

Rankings synthesized from community evidence and open benchmarks. See methodology. Not driven by vendor marketing.