Claude Sonnet 4.6 vs GPT-5
Claude Sonnet 4.6 (2026) and GPT-5 (2025) are frontier-tier reasoning models from Anthropic and OpenAI. Claude Sonnet 4.6 ships a 1m-token context window, while GPT-5 ships a 400k-token context window. On SWE-bench Verified, Claude Sonnet 4.6 leads by 4.7 pts. On pricing, GPT-5 costs $1.25/1M input tokens versus $3/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
GPT-5 is ~140% cheaper at $1.25/1M; pay for Claude Sonnet 4.6 only for coding workflow support.
Decision scorecard
Local evidence first| Signal | Claude Sonnet 4.6 | GPT-5 |
|---|---|---|
| Best for | reasoning-heavy apps, multimodal apps, and tool-calling agents | reasoning-heavy apps, multimodal apps, and tool-calling agents |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Agents |
| Context window | 1m | 400k |
| Cheapest output | $15/1M tokens | $10/1M tokens |
| Provider routes | 6 tracked | 4 tracked |
| Shared benchmarks | SWE-bench Verified leader | 4 shared |
Decision tradeoffs
- Claude Sonnet 4.6 holds a shared-benchmark lead on SWE-bench Verified, ahead by 4.7 points.
- Claude Sonnet 4.6 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Claude Sonnet 4.6 has broader tracked provider coverage for fallback and procurement flexibility.
- Claude Sonnet 4.6 uniquely exposes Computer use and Parallel agents in local model data.
- Local decision data tags Claude Sonnet 4.6 for Coding, RAG, and Agents.
- GPT-5 holds a shared-benchmark lead on AIME 2025, ahead by 0.6 points.
- GPT-5 has the lower cheapest tracked output price at $10/1M tokens.
- Local decision data tags GPT-5 for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Claude Sonnet 4.6
$6,150
Cheapest tracked route/tier: OpenRouter
GPT-5
$3,500
Cheapest tracked route/tier: Replicate API
Estimated monthly gap: $2,650. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on OpenRouter and Vercel AI Gateway; start route-level A/B tests there.
- GPT-5 is $5/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Computer use and Parallel agents before moving production traffic.
- Provider overlap exists on OpenRouter and Vercel AI Gateway; start route-level A/B tests there.
- Claude Sonnet 4.6 is $5/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Claude Sonnet 4.6 adds Computer use and Parallel agents in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2026-02-17 | 2025-08-07 |
| Context window | 1m | 400k |
| Parameters | — | — |
| Architecture | Decoder Only | Decoder Only |
| License | Proprietary | Proprietary |
| Openness | Proprietary | Proprietary |
| Commercial use | Commercial use: conditional | Commercial use: conditional |
| Knowledge cutoff | 2025-08 | 2024-09 |
Pricing and availability
| Pricing attribute | Claude Sonnet 4.6 | GPT-5 |
|---|---|---|
| Input price | $3/1M tokens | $1.25/1M tokens |
| Output price | $15/1M tokens | $10/1M tokens |
| Providers |
Capabilities
| Capability | Claude Sonnet 4.6 | GPT-5 |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | Yes | Yes |
| Reasoning | Yes | Yes |
| Function calling | Yes | Yes |
| Tool use | Yes | Yes |
| Structured outputs | Yes | Yes |
| Code execution | Yes | Yes |
| IDE integration | No | No |
| Computer use | Yes | No |
| Parallel agents | Yes | No |
Benchmarks
| Benchmark | Claude Sonnet 4.6 | GPT-5 |
|---|---|---|
| SWE-bench Verified | 79.6 | 74.9 |
| Google-Proof Q&A | 89.9 | 88.4 |
| AIME 2025 | 94.0 | 94.6 |
| MMMU Pro | 75.6 | 78.4 |
Deep dive
On shared benchmark coverage, SWE-bench Verified has Claude Sonnet 4.6 at 79.6 and GPT-5 at 74.9, with Claude Sonnet 4.6 ahead by 4.7 points; Google-Proof Q&A has Claude Sonnet 4.6 at 89.9 and GPT-5 at 88.4, with Claude Sonnet 4.6 ahead by 1.5 points; AIME 2025 has Claude Sonnet 4.6 at 94 and GPT-5 at 94.6, with GPT-5 ahead by 0.6 points. The largest visible gap is 4.7 points on SWE-bench Verified, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint is close: both models cover vision, multimodal input, reasoning mode, function calling, and tool use. That makes context budget, benchmark fit, and provider maturity more important than a simple checklist. If your application depends on one integration detail, verify it against the provider route you plan to use, not just the base model listing.
For cost, Claude Sonnet 4.6 lists $3/1M input and $15/1M output tokens on the cheapest tracked provider, while GPT-5 lists $1.25/1M input and $10/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts GPT-5 lower by about $2.72 per million blended tokens. Availability is 6 providers versus 4, so concentration risk also matters.
Choose Claude Sonnet 4.6 when coding workflow support, larger context windows, and broader provider choice are central to the workload. Choose GPT-5 when coding workflow support and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, Claude Sonnet 4.6 or GPT-5?
Claude Sonnet 4.6 supports 1m tokens, while GPT-5 supports 400k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Which is cheaper, Claude Sonnet 4.6 or GPT-5?
GPT-5 is cheaper on tracked token pricing. Claude Sonnet 4.6 costs $3/1M input and $15/1M output tokens. GPT-5 costs $1.25/1M input and $10/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Claude Sonnet 4.6 or GPT-5 open source?
Claude Sonnet 4.6 is listed under Proprietary. GPT-5 is listed under Proprietary. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Claude Sonnet 4.6 or GPT-5?
Both Claude Sonnet 4.6 and GPT-5 expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Which is better for multimodal input, Claude Sonnet 4.6 or GPT-5?
Both Claude Sonnet 4.6 and GPT-5 expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Where can I run Claude Sonnet 4.6 and GPT-5?
Claude Sonnet 4.6 is available on OpenRouter, Anthropic, AWS Bedrock, GCP Vertex AI, and Microsoft Foundry. GPT-5 is available on Replicate API, OpenRouter, OpenAI API, and Vercel AI Gateway. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-15. Data sourced from public model cards and provider documentation.