Compare/GPT-5.1 Codex (high) vs Claude Sonnet 5 (Non-reasoning, High Effort)

GPT-5.1 Codex (high)vsClaude Sonnet 5 (Non-reasoning, High Effort)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

OpenAI

GPT-5.1 Codex (high)

Input
$1.25/M
Output
$10/M
Speed
189 tok/s
TTFT
4.13s
Anthropic

Claude Sonnet 5 (Non-reasoning, High Effort)

Input
$2/M
Output
$10/M
Speed
TTFT

Winner by Category

Cheaper
GPT-5.1 Codex (high)
Faster (tok/s)
GPT-5.1 Codex (high)
Lower Latency
Claude Sonnet 5 (Non-reasoning, High Effort)
Benchmarks (8-3)
GPT-5.1 Codex (high)

Pricing Comparison

MetricGPT-5.1 Codex (high)Claude Sonnet 5 (Non-reasoning, High Effort)
Input ($/M tokens)$1.25$2
Output ($/M tokens)$10$10
Cost for 1M input + 100K output tokens:
GPT-5.1 Codex (high)$2.25
Claude Sonnet 5 (Non-reasoning, High Effort)$3.00

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-5.1 Codex (high)
189 tok/s
Claude Sonnet 5 (Non-reasoning, High Effort)
Time to First Token (seconds) — lower is better
GPT-5.1 Codex (high)
4.13s
Claude Sonnet 5 (Non-reasoning, High Effort)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
34.741.7
Coding Index
66.4
Math Index
95.7
GPQA Diamond
86.0%80.0%
MMLU-Pro
86.0%
LiveCodeBench
84.9%
AIME 2025
95.7%
MATH-500
Humanity's Last Exam
23.4%17.8%
SciCode
40.2%48.6%
IFBench
70.0%
TerminalBench
34.8%
GPT-5.1 Codex (high)8 wins
3 winsClaude Sonnet 5 (Non-reasoning, High Effort)

Frequently Asked Questions

Which is cheaper, GPT-5.1 Codex (high) or Claude Sonnet 5 (Non-reasoning, High Effort)?

GPT-5.1 Codex (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.44/M tokens vs $4.00/M for Claude Sonnet 5 (Non-reasoning, High Effort).

Which model performs better on benchmarks?

GPT-5.1 Codex (high) wins 8 out of 12 benchmarks compared to 3 for Claude Sonnet 5 (Non-reasoning, High Effort). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GPT-5.1 Codex (high) generates tokens faster at 189 tok/s vs 0 tok/s. However, Claude Sonnet 5 (Non-reasoning, High Effort) has lower time-to-first-token (0.00s vs 4.13s).

When should I use GPT-5.1 Codex (high) vs Claude Sonnet 5 (Non-reasoning, High Effort)?

Choose based on your priorities: GPT-5.1 Codex (high) for lower cost, GPT-5.1 Codex (high) for stronger benchmark performance, and GPT-5.1 Codex (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.