Claude Opus 5 vs GPT-6.1 Sol
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Opus 534.3
GPT-6.1 Sol48
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 568.9
GPT-6.1 Sol · max72.3
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Opus 5 · max1,689
GPT-6.1 Sol · max1,753
SWE-bench Pro (v2 full) SWE-bench Pro (v2 full): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate
Opus 5 · xhigh99.4
GPT-6.1 Sol · xhigh96.1
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Opus 551.5
GPT-6.1 Sol53.2
Terminal-Bench Science 0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal
Opus 5 · max28.6
GPT-6.1 Sol · max58.1
FrontierCode 1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements
Opus 5—
GPT-6.1 Sol · max49.1
SWE-bench Pro (v2 hard) SWE-bench Pro (v2 hard): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate
Opus 5 · xhigh98
GPT-6.1 Sol—
MultiLangBenchlab MultiLangBench: Models build a SQLite-compatible database engine in 20 programming languages
Opus 5—
GPT-6.1 Sol67.5
| Benchmark | Opus 5 | GPT-6.1 Sol |
|---|---|---|
| Terminal-Bench 4.0 | 34.3 | 48 |
| DeepSWE 1.1 | 68.9 | 72.3 · max |
| WebDev Arena | 1,689 · max | 1,753 · max |
| SWE-bench Pro (v2 full) | 99.4 · xhigh | 96.1 · xhigh |
| SciCode | 51.5 | 53.2 |
| Terminal-Bench Science 0.1 | 28.6 · max | 58.1 · max |
| FrontierCode 1.1 | — | 49.1 · max |
| SWE-bench Pro (v2 hard) | 98 · xhigh | — |
| MultiLangBenchlab | — | 67.5 |
Specs
| Spec | Opus 5 | GPT-6.1 Sol |
|---|---|---|
| Input, per 1M | $5 | $2 |
| Output, per 1M | $25 | $10 |
| Cost per task? | $2.19 | $0.21 |
| Speed, tok/s | 55 | 45 |
| Context | 1M | 1.05M |
| Weights | Closed | Closed |
| Released | Jul 2026 | Sep 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | Partial |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ✓ |
| Run code | ? | ✓ |
| Use a computer | ? | ✓ |
What breaks when you switch
Opus 5 → GPT-6.1 Sol
Remove unsupported parameters›
With reasoning enabled, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses message.output_text.logprobs includes.
Responses API for tool calling · Chat Completions›
Use Responses for tools; Chat Completions supports this model without tool calling.
No none or minimal reasoning›
The none and minimal reasoning efforts are unsupported; choose low, medium, high, xhigh or max.
More than 272K input tokens›
Prompts above 272K input tokens charge 2× input and cache rates and 1.5× output rates for the entire request.
Cache writes billed at 1.25x›
Cache writes cost 1.25× the uncached input token rate.
Ultrafast prices 6x Standard›
Ultrafast mode costs 6× Standard token prices.
GPT-6.1 Sol → Opus 5