How do Claude Opus 5 and Claude Sonnet 5 compare on coding benchmarks?

The comparison table shows SWE-bench, SWE-Pro, SWE-Atlas, Terminal-Bench, DeepSWE, and coding agent index scores for both Claude Opus 5 and Claude Sonnet 5 when publicly disclosed.

LLM Comparison

Claude Opus 5 vs Claude Sonnet 5: benchmark scores, pricing & comparison.

Q: Which is better: Claude Opus 5 or Claude Sonnet 5?

AskClash compares Claude Opus 5 and Claude Sonnet 5 side by side across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, and context window so you can see which model wins on each benchmark.

Side-by-side Claude Opus 5 vs Claude Sonnet 5 comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.

Open live leaderboard Claude Opus 5 model page Claude Sonnet 5 model page

Rank #1 vs #8AskClash overall scores 94.2 vs 75.3.

Pricing $5.00/$25.0 vs $3.00/$15.0Input and output token prices per 1M tokens when published.

Proprietary vs ProprietaryAnthropic vs Anthropic.

Claude Opus 5 vs Claude Sonnet 5 benchmark comparison

Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.

Metric	Claude Opus 5	Claude Sonnet 5
Overall Score	94.2	75.3
Leaderboard Rank	#1	#8
RWT	9.0	8.5
HLE	64.7	57.4
GPQA	—	91.1
SWE-bench	96.0	85.2
SWE-Pro	79.2	63.2
Terminal-Bench	—	80.4
DeepSWE	68.8	53.8
OSWorld	—	81.2
MCP Atlas	85.8	—
CharXiv	—	88.3
MMMU-Pro	—	77.3
ARC-AGI 2	90.4	—
Input Price (per 1M tokens)	$5.00	$3.00
Output Price (per 1M tokens)	$25.0	$15.0
Context Window	1M	1M
Benchmarks Published	8	12

Claude Opus 5 vs Claude Sonnet 5 head-to-head charts

Claude Opus 5 leads 6 and Claude Sonnet 5 leads 0 of 6 shared benchmarks. Claude Sonnet 5 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Claude Opus 5Claude Sonnet 5

Overall

94.2Claude Opus 5

75.3Claude Sonnet 5

RWT

9.0Claude Opus 5

8.5Claude Sonnet 5

HLE

64.7Claude Opus 5

57.4Claude Sonnet 5

SWE-bench

96.0Claude Opus 5

85.2Claude Sonnet 5

SWE-Pro

79.2Claude Opus 5

63.2Claude Sonnet 5

DeepSWE

68.8Claude Opus 5

53.8Claude Sonnet 5

Claude Opus 5

Input$5.00

Output$25.0

Workload$10

Context1M

Claude Sonnet 5

Input$3.00

Output$15.0

Workload$6.00

Context1M

Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.

More Claude Opus 5 and Claude Sonnet 5 comparisons

Explore how Claude Opus 5 and Claude Sonnet 5 stack up against other top-ranked LLMs.

Claude Opus 5 vs Claude Fable 5 Claude Fable 5 vs Claude Sonnet 5 Claude Opus 5 vs GPT-5.6 Sol GPT-5.6 Sol vs Claude Sonnet 5 Claude Opus 5 vs Claude Opus 4.8 Claude Opus 4.8 vs Claude Sonnet 5 Claude Opus 5 vs Claude Opus 4.7 Claude Opus 4.7 vs Claude Sonnet 5 Claude Opus 5 vs Kimi K3 Kimi K3 vs Claude Sonnet 5

How to read this comparison

Benchmark scores

Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.

Token pricing

Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.

Coverage matters

Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.

This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.