text model comparison
Claude Sonnet 5 vs GPT-4.1
Claude Sonnet 5 and GPT-4.1 are both current text models, from Anthropic and OpenAI. Both cost $2 per 1M input tokens. On Arena Text, Claude Sonnet 5 scores 1461 Elo and GPT-4.1 1415 Elo (Arena, measured October 8, 2026). Both accept about 1.05M tokens of context (1,047,576 and 1,000,000).
Data verified October 12, 2026 · Dataset 2026-10-12
Side by side
Standard-tier prices in effect today. The better value in each row is highlighted.
| Fact | Claude Sonnet 5 | GPT-4.1 |
|---|---|---|
| Price per 1M input tokens | $2 | $2 |
| Price per 1M output tokens | $10 | $8 (better) |
| Cost of 10M input and 2M output tokens | $40 | $36 (better) |
| Arena Text | 1461 Elo (#25 of 39) (better) | 1415 Elo (#36 of 39) |
| GPQA Diamond | 90.5% (#23 of 37) (better) | 66.9% (#35 of 37) |
| FrontierMath Tiers 1-3 (v2) | 65.6% (#24 of 37) (better) | 6% (#37 of 37) |
| SimpleQA Verified | 33.7% (#27 of 34) (better) | 31.1% (#29 of 34) |
| LiveBench Overall | 74.85 points (#4 of 5) | Not measured |
| Provider | Anthropic | OpenAI |
| Release date | June 30, 2026 | April 14, 2025 |
| Access | API only | API only |
| Context window | 1,000,000 tokens | 1,047,576 tokens |
| Max output | 128,000 tokens | 32,768 tokens |
| Input | text | text, image |
| Output | text | text |
Scores:Arena · 2026-10-12Epoch AI · 2026-10-12LiveBench · 2026-06-25
When to choose each
Claude Sonnet 5
Best for
- Agentic coding evaluations with current introductory API pricing
Watch out for
- The launch price is introductory through 2026-08-31; refresh pricing before evaluating workloads after that date
GPT-4.1
Best for
- Long-context API trials using text and image inputs
Watch out for
- Not in the pinned LiveBench snapshot; its independent scores here come from Epoch AI's own GPQA Diamond, FrontierMath and SimpleQA Verified runs
Claude Sonnet 5 vs GPT-4.1 FAQ
Which is cheaper, Claude Sonnet 5 or GPT-4.1?
Both cost $2 per 1M input tokens. For 10M input and 2M output tokens, Claude Sonnet 5 costs $40 and GPT-4.1 $36 at standard rates.
Which scores higher on independent benchmarks, Claude Sonnet 5 or GPT-4.1?
Claude Sonnet 5 leads on Arena Text, 1461 Elo to 1415 Elo; Claude Sonnet 5 leads on GPQA Diamond, 90.5% to 66.9%; Claude Sonnet 5 leads on FrontierMath Tiers 1-3 (v2), 65.6% to 6%. Scores are independent evaluations, not either vendor's launch figures.
Which has the larger context window, Claude Sonnet 5 or GPT-4.1?
Both accept about 1.05M tokens of context (1,047,576 and 1,000,000).
Related comparisons
Production evaluation
Choosing between Claude Sonnet 5 and GPT-4.1?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty