Claude Opus 5 vs GPT-6.1 Sol

Claude Opus 5 by Anthropic · GPT-6.1 Sol by OpenAI · 27 shared benchmarks

Claude Opus 5

74.9

#5 · 100%

GPT-6.1 Sol

73.0

#6 · 100%

SI Score, rank and confidence side by side

Pillars — Claude Opus 5

Coding 69.7 / 65.0

Math 86.9 / 93.0

Preference 81.9 / 77.3

Reasoning 84.3 / 87.5

Right-hand value is GPT-6.1 Sol.

The basics

Attribute	Claude Opus 5	GPT-6.1 Sol
Input price / 1M	$5.00	$2.00
Output price / 1M	$25.00	$10.00
Context window	1M	1.1M
Released	Jul 24, 2026	Sep 29, 2026
Open weights	Closed	Closed

Shared benchmarks

27 in common

Only benchmarks both models have are compared. Raw values are in each benchmark's own unit; a direct comparison requires matching evaluation conditions. All reported source/variant rows are shown; no raw-result winner is assigned across unmatched harnesses. Sources and dates sit behind every dotted number.

Which should you choose?

What the data says — heuristics from the numbers above, not a verdict:

For reasoning, GPT-6.1 Sol leads by 3.2 normalized points.
For math, GPT-6.1 Sol leads by 6.2 normalized points.
For coding, Claude Opus 5 leads by 4.7 normalized points.
For preference, Claude Opus 5 leads by 4.6 normalized points.
GPT-6.1 Sol has the lower input-token price ($2.00 vs $5.00 per 1M).
Confidence differs: Claude Opus 5 100% vs GPT-6.1 Sol 100% — pending sources can still move either score.

Benchmark	Claude Opus 5	GPT-6.1 Sol	Conditions
arc agi v1 public eval	99%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-high 99%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-max	98.3%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-high 96.4%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-low 98.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-max 97.9%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-medium 98.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-xhigh	Check variant and harness
arc agi v1 semi private	97.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-high 97.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-max	98.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-high 93.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-low 96.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-max 95.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-medium 98.5%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-xhigh	Check variant and harness
arc agi v2 public eval	93.2%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-high 97.1%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-max	95.8%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-high 77.8%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-low 97.1%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-max 90.6%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-medium 95.8%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-xhigh	Check variant and harness
arc agi v2 semi private	88.3%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-high 90.4%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' output effort. [variant] anthropic-claude-opus-5-max	91.7%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-high 76.7%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-low 94.2%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-max 86.7%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-medium 91.7%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-xhigh	Check variant and harness
arc agi v3 semi private	30.2%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' output effort. [variant] anthropic-claude-opus-5-high	26.7%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-high 3.9%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-low 52.7%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-max 10.6%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-medium 39.9%ARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. [variant] openai-gpt-6-1-sol-xhigh	Check variant and harness
frontiermath tier 4 v2	73.2%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	100%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	Check variant and harness
frontiermath tiers 1 3 v2	85.6%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	93.7%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	Check variant and harness
gpqa diamond	92.9%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] 87.9%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] low 93.9%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	95.4%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	Check variant and harness
livebench coding code completion 2026_06_25	82.6%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	82.6%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench coding code generation 2026_06_25	80.3%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	78.9%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench coding javascript 2026_06_25	77.3%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	63.6%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench coding python 2026_06_25	75%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	60%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench coding typescript 2026_06_25	43.3%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	46.7%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench math amps hard 2026_06_25	99.0%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	98%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench math integrals with game 2026_06_25	97%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	99%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench math math comp 2026_06_25	94.1%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	97.1%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench math olympiad 2026_06_25	92.8%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	91.9%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench math simplify 2026_06_25	61.6%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	68.2%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench reasoning connections 2026_06_25	99.3%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	100%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench reasoning consecutive events 2026_06_25	77.6%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	91.3%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench reasoning logic with navigation 2026_06_25	86%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	82%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench reasoning spatial 2026_06_25	100%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	98%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench reasoning theory of mind 2026_06_25	78.8%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	86.5%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
livebench reasoning zebra puzzle 2026_06_25	100%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	100%LiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25	Check variant and harness
lmarena text	1502.1 eloPublished source fact [variant] text / overall	1445.6 eloPublished source fact [variant] text / overall	Check variant and harness
otis mock aime 2024 2025	97.8%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] 93.3%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] low 98.9%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	100%Epoch-owned evaluation mean score; scores only, no benchmark questions [variant] max	Check variant and harness
terminal bench v4 0	50.3%Terminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; high 34.9%Terminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; low 51.8%Terminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; max 44.9%Terminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; medium 53.9%Terminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; xhigh	58.2%Terminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; max	Check variant and harness