Claude Sonnet 5.5 vs Gemini 4 Argon
Claude Sonnet 5.5 and Gemini 4 Argon cost the same today, $2 input and $10 output per 1M tokens, and Sonnet 5.5 scores higher on the one benchmark both have: 70.6% against 57.4% on Terminal-Bench 4.0. From 1 December 2026 the Argon price rises to $4 and $20, twice what Sonnet costs.
The same price until December
Until 30 November every rate matches, cached input included at $0.10, so our sessions cost the same to the cent: $10.80 for the feature session, $2.59 with 90% of prompts cached, $97.50 for a long agent day. Filling the whole window once costs $2.10 on Argon and $2.00 on Sonnet, because the Argon window is a little larger.
From 1 December the Argon input and output prices double. The price note we cite does not say what happens to its cached rate.
Context, output and inputs
Argon reads up to 1.05M tokens and writes up to 66K in one reply; Sonnet 5.5 reads 1M and writes up to 128K. Argon also takes video, audio and PDF files; Sonnet takes text and images.
Scores and dates
Terminal-Bench 4.0: Sonnet 70.6%, Argon 57.4%, the Argon figure from Google's comparison table as reproduced by HackerNoon. Sonnet also has 46.2% on FrontierCode 1.1 and 64.5% on Humanity's Last Exam with tools; we have neither for Argon.
Anthropic released Sonnet 5.5 on 28 September 2026 and Google released Argon two days later, on 30 September. Claude Code vs Gemini CLI compares the agents each runs in.
Side by side
| Claude Sonnet 5.5 | Gemini 4 Argon | |
|---|---|---|
| Maker | Anthropic | |
| Released | 28 September 2026[1] | 30 September 2026[2] |
| Context window | 1M tokens[1] | 1.05M tokens[3] |
| Max output | 128K tokens[1] | 66K tokens[3] |
| Input price | $2 per 1M tokens[1] | $2 per 1M tokens[4] |
| Output price | $10 per 1M tokens[1] | $10 per 1M tokens[4] |
| Cached input | $0.10 per 1M tokens[5] | $0.10 per 1M tokens[4] |
| Long prompts | One price | One price |
| Price change | None announced | Introductory price through 30 November 2026; $4 input and $20 output per 1M tokens from 1 December 2026.[4] |
| Open weights | No[1] Offered through the Claude API and cloud platforms; no weights are published. | No[6] Served through the Gemini API; no weights are published. |
| Reads | text, image[1] | text, image, video, audio, pdf[3] |
Benchmarks
Scores as the makers published them, each with its source and date. Makers run these at different settings, so read a gap of a few points as a tie.
| Benchmark | Claude Sonnet 5.5 | Gemini 4 Argon |
|---|---|---|
| Terminal-Bench 4.0Agentic coding tasks in a real terminal. | 70.6%[7] | 57.4%[8] Google's comparison table as reproduced by HackerNoon. |
| FrontierCode 1.1 (Main)Hard software engineering tasks. | 46.2%[7] Max effort. | Not published |
| Humanity's Last Exam (with tools)Expert-level questions across many fields, tools allowed. | 64.5%[7] | Not published |
What a coding session costs
Our own estimate from the list prices above, for three sessions we define: a coding agent resends the conversation with every call, so prompts are large and grow. "Cached" assumes 90% of prompt tokens are read from the prompt cache and leaves out cache write fees. A long-prompt price applies when a call's prompt is over its threshold. Work out your own mix with the token cost calculator.
| Session | Claude Sonnet 5.5 | Claude Sonnet 5.5 cached | Gemini 4 Argon | Gemini 4 Argon cached |
|---|---|---|---|---|
| Quick fix10 calls of 25K prompt and 1.5K output tokens | $0.65 | $0.22 | $0.65 | $0.22 |
| Feature session60 calls of 80K prompt and 2K output tokens | $10.80 | $2.59 | $10.80 | $2.59 |
| Long agent day300 calls of 150K prompt and 2.5K output tokens | $97.50 | $20.55 | $97.50 | $20.55 |
Value for money and release gap
Gemini 4 Argon came out 2 days later. Price per point divides our feature-session cost by a published score: lower means more score for the money. It is a rough lens, not a ranking.
| Measure | Claude Sonnet 5.5 | Gemini 4 Argon |
|---|---|---|
| Input tokens per $1 | 500K | 500K |
| Filling the whole context window once | $2.00 | $2.10 |
| Feature session per point of Terminal-Bench 4.0 | $0.15 | $0.19 |
Questions
Do Sonnet 5.5 and Gemini 4 Argon cost the same?
Until 30 November 2026, yes: $2 per 1M input tokens, $10 per 1M output and $0.10 cached. From 1 December 2026 Argon costs $4 and $20.
Which scores higher on Terminal-Bench 4.0?
Claude Sonnet 5.5, with 70.6% against 57.4% for Gemini 4 Argon, a lead of 13.2 points.
Can both read images and documents?
Both read text and images. Gemini 4 Argon also takes video, audio and PDF files.
Most compared
Any other two models: pick them in the lists at the top of the page.
- Claude Opus 5.5 vs Claude Sonnet 5.5
- Claude Sonnet 5 vs Claude Sonnet 5.5
- Claude Haiku 5.5 vs Claude Sonnet 5.5
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Claude Opus 5.5 vs Gemini 4 Argon
- Gemini 4 Argon vs GPT-6.1 Sol
- Gemini 3.1 Pro Preview vs Gemini 4 Argon
- Claude Sonnet 5.5 vs Kimi K3
- Claude Sonnet 5.5 vs GLM-5.3
- Claude Fable 5.1 vs Claude Opus 5.5
- Claude Opus 5 vs Claude Opus 5.5
- Claude Haiku 4.5 vs Claude Haiku 5.5
- Claude Fable 5 vs Claude Fable 5.1
- Claude Opus 5.5 vs GPT-6.1 Sol
- Claude Opus 5.5 vs GPT-5.6 Sol
- Claude Fable 5.1 vs GPT-6 Astra
- Claude Opus 5.5 vs GPT-6 Astra
- Claude Haiku 5.5 vs GPT-6 Luna
- GPT-6.1 Sol vs GPT-6 Sol
- GPT-6.1 Sol vs GPT-6 Astra
- Claude Opus 5.5 vs Gemini 3.1 Pro Preview
- Claude Haiku 5.5 vs Gemini 3.8 Flash
- Claude Opus 5.5 vs Grok 4.7
- Claude Opus 5.5 vs DeepSeek V4 Pro
More tools
Sources
- platform.claude.com: docs/en/models/sonnet-5-5/overview, read
- blog.google: innovation-and-ai/models-and-research/gemini-models/gemini-4-argon, read
- ai.google.dev: gemini-api/docs/models/gemini-4-argon, read
- ai.google.dev: gemini-api/docs/pricing, read
- platform.claude.com: docs/en/about-claude/pricing, read
- ai.google.dev: gemini-api/docs/models, read
- anthropic.com: claude-sonnet-5-5, read
- hackernoon.com: gemini-4-argon-how-does-it-do-against-gpt-6-astra-and-claude, read
Numbers from the makers' own pages, checked by hand, last read . List prices in US dollars before tax. Spotted a mistake? office@shuriken.sh.
Made by Shuriken, the harness for coding agents. Its hot swapping moves your chats to another of your accounts or API keys when one nears its limit. Use only accounts you own and are entitled to use.
Try Shuriken on your own computerYou're signed in
Add your Claude, Codex and Gemini accounts once. Shuriken switches between them so your agents keep working.Your accounts, projects and chats are in the app.
Coming soon