Claude Opus 4.7 vs Gemini 4 Argon
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 4.7—
Gemini 4 Argon57.1
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Opus 4.71,558
Gemini 4 Argon1,678
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.7 · max49.3
Gemini 4 Argon—
FrontierCode 1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements
Opus 4.7—
Gemini 4 Argon43.5
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 4.7—
Gemini 4 Argon99.2
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 4.7—
Gemini 4 Argon92.2
DeepSWE 1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.740.3
Gemini 4 Argon—
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Opus 4.7—
Gemini 4 Argon61.8
Terminal-Bench Science 0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal
Opus 4.7—
Gemini 4 Argon52.9
Terminal-Bench Hard (version unstated) Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal
Opus 4.754.5
Gemini 4 Argon—
MirrorCode MirrorCode: Agents reimplement software projects by observing their behavior
Opus 4.731.1
Gemini 4 Argon—
| Benchmark | Opus 4.7 | Gemini 4 Argon |
|---|---|---|
| Terminal-Bench 4.0 | — | 57.1 |
| WebDev Arena | 1,558 | 1,678 |
| DeepSWE 1.1 | 49.3 · max | — |
| FrontierCode 1.1 | — | 43.5 |
| SWE-bench Pro (v2 full) | — | 99.2 |
| SWE-bench Pro (v2 hard) | — | 92.2 |
| DeepSWE 1 | 40.3 | — |
| SciCode | — | 61.8 |
| Terminal-Bench Science 0.1 | — | 52.9 |
| Terminal-Bench Hard (version unstated) | 54.5 | — |
| MirrorCode | 31.1 | — |
Specs
| Spec | Opus 4.7 | Gemini 4 Argon |
|---|---|---|
| Input, per 1M | $5 | !$2 |
| Output, per 1M | $25 | !$10 |
| Cost per task? | — | $1.99 |
| Speed, tok/s | 59 | 84 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Apr 2026 | Oct 2026 |
| See images | ✓ | ✓ |
| Read PDFs | 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 4.7 → Gemini 4 Argon
Synchronous output stops at 65,536›
With background false, output limits above 65,536 tokens return HTTP 400; stay at or below that limit.
Sampling parameters are ignored›
temperature, top_p and top_k are ignored; remove them from requests.
No explicit caching›
Explicit caching is unavailable; omit explicit cache requests.
Gemini 4 Argon → Opus 4.7
Nothing known.