Claude Opus 5.5 vs Gemini 4 Argon
Claude Opus 5.5 scored 66.4% on Terminal-Bench 4.0 against 57.4% for Gemini 4 Argon. Argon costs half as much for now, $2 input and $10 output per 1M tokens, but that is an introductory price through 30 November 2026; from 1 December 2026 it is $4 and $20, the same as Opus 5.5.
The price changes on 1 December
Until the end of November, our feature session costs $10.80 on Argon and $21.60 on Opus 5.5, or $2.59 against $5.18 with 90% of prompts cached. A long agent day is $97.50 against $195.
From 1 December the input and output prices match, so uncached sessions will cost the same on both. The price note we cite does not say whether the cached rate changes too.
Size and what each reads
Argon reads up to 1.05M tokens but writes at most 66K in one reply; Opus 5.5 reads 1M and writes up to 128K. Argon takes text, images, video, audio and PDF files, Opus 5.5 text and images.
Scores and dates
The Argon Terminal-Bench figure comes from Google's comparison table as reproduced by HackerNoon, and Opus 5.5 ran at xhigh effort. We have no FrontierCode 1.1 or Humanity's Last Exam score for Argon; Opus 5.5 has 54.4% and 67.7%.
Anthropic released Opus 5.5 on 22 September 2026 and Google released Argon eight days later, on 30 September. The agents differ as well as the models: Claude Code vs Gemini CLI.
Side by side
| Claude Opus 5.5 | Gemini 4 Argon | |
|---|---|---|
| Maker | Anthropic | |
| Released | 22 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 | $4 per 1M tokens[1] | $2 per 1M tokens[4] |
| Output price | $20 per 1M tokens[1] | $10 per 1M tokens[4] |
| Cached input | $0.20 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 Opus 5.5 | Gemini 4 Argon |
|---|---|---|
| Terminal-Bench 4.0Agentic coding tasks in a real terminal. | 66.4%[7] Run at xhigh effort. | 57.4%[8] Google's comparison table as reproduced by HackerNoon. |
| FrontierCode 1.1 (Main)Hard software engineering tasks. | 54.4%[7] Max effort. | Not published |
| Humanity's Last Exam (with tools)Expert-level questions across many fields, tools allowed. | 67.7%[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 Opus 5.5 | Claude Opus 5.5 cached | Gemini 4 Argon | Gemini 4 Argon cached |
|---|---|---|---|---|
| Quick fix10 calls of 25K prompt and 1.5K output tokens | $1.30 | $0.45 | $0.65 | $0.22 |
| Feature session60 calls of 80K prompt and 2K output tokens | $21.60 | $5.18 | $10.80 | $2.59 |
| Long agent day300 calls of 150K prompt and 2.5K output tokens | $195 | $41.10 | $97.50 | $20.55 |
Value for money and release gap
Gemini 4 Argon came out 8 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 Opus 5.5 | Gemini 4 Argon |
|---|---|---|
| Input tokens per $1 | 250K | 500K |
| Filling the whole context window once | $4.00 | $2.10 |
| Feature session per point of Terminal-Bench 4.0 | $0.33 | $0.19 |
Questions
Is Gemini 4 Argon cheaper than Claude Opus 5.5?
Until 30 November 2026, yes: $2 per 1M input tokens and $10 per 1M output, half of the $4 and $20 for Opus 5.5. From 1 December 2026 the Argon list price is $4 and $20, the same as Opus.
Which is better at agentic coding, Opus 5.5 or Gemini 4 Argon?
On Terminal-Bench 4.0, Opus 5.5 scored 66.4% and Gemini 4 Argon 57.4%. That is the only benchmark in our set with a score for both.
Which can write longer replies?
Claude Opus 5.5: up to 128K output tokens in one reply, against 66K for Gemini 4 Argon. Argon has the slightly larger context window, 1.05M tokens against 1M.
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 Fable 5.1 vs Claude Opus 5.5
- Claude Opus 5 vs Claude Opus 5.5
- Claude Opus 5.5 vs GPT-6.1 Sol
- Claude Opus 5.5 vs GPT-5.6 Sol
- Claude Opus 5.5 vs GPT-6 Astra
- Claude Sonnet 5.5 vs Gemini 4 Argon
- Claude Opus 5.5 vs Gemini 3.1 Pro Preview
- Gemini 4 Argon vs GPT-6.1 Sol
- Gemini 3.1 Pro Preview vs Gemini 4 Argon
- Claude Opus 5.5 vs Grok 4.7
- Claude Opus 5.5 vs DeepSeek V4 Pro
- Claude Sonnet 5 vs Claude Sonnet 5.5
- Claude Haiku 5.5 vs Claude Sonnet 5.5
- Claude Haiku 4.5 vs Claude Haiku 5.5
- Claude Fable 5 vs Claude Fable 5.1
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Claude Fable 5.1 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 Haiku 5.5 vs Gemini 3.8 Flash
- Claude Sonnet 5.5 vs Kimi K3
- Claude Sonnet 5.5 vs GLM-5.3
More tools
Sources
- platform.claude.com: docs/en/models/opus-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-opus-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