← comparisons · head to head
Gemini 4 Carbon vs Gemini 4 Argon
Gemini 4 Carbon scores higher than Gemini 4 Argon on all 4 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Gemini 4 Carbon is at 94.6 and Gemini 4 Argon at 79.7 (out of 100).
Scores as published by each board; table composed November 10, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Gemini 4 Carbon | Gemini 4 Argon | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,768 | 1,682.6 | Gemini 4 Carbon |
| LLM Stats LLM Stats Score · composite (0-100), their rendered top 15 | 57.5 | 53.8 | Gemini 4 Carbon |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 70.5 | 69.4 | Gemini 4 Carbon |
| Artificial Analysis intelligence index · measured runs only | 59.4 | 50.4 | Gemini 4 Carbon |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
For coding
On the ArtificialWatch coding index, Gemini 4 Carbon is at 91.8 (#2 of 47) and Gemini 4 Argon at 95.2 (#1). Gemini 4 Carbon scores higher on 1 of the 2 coding boards that rate both and Gemini 4 Argon on 1.
| Coding board | Gemini 4 Carbon | Gemini 4 Argon |
|---|---|---|
| LMArena · Coding | 1,563.4 | 1,540 |
| Vals Vibe Code Bench | 89.1 | 91.9 |
Gemini 4 Carbon at a glance
- Developer
- Status
- Live since November 10, 2026
Live — Nov 10 · GA on the Gemini API as gemini-4-carbon (Google's release notes, Nov 10) and in Google AI Studio, paid tier only, no free tier · introductory $2 / $10 per 1M through Nov 30, then $4 / $20 from Dec 1; cached input $0.10, then $0.20, implicit caching only · unified 1,048,576-token context; max output 65,536 by default, up to about 1M with long decode · text, image, video, audio and PDF in, text out · thinking levels low / medium / high, default medium; Google says Carbon spends more thinking tokens per turn than Argon at the same per-token price · Batch, Flex and Priority inference · Google calls it its strongest reasoning model, for agentic coding, multimodal knowledge work, scientific reasoning and cybersecurity defense · Gemini app: screenshots from @LuminaBench and @Mr_Salio show it on Ultra plans first, not confirmed by Google · AW's radar fired at 15:46 UTC · history: announced Oct 28 for cyber defenders and Fairwind partners, alert fired 18:58 UTC; Artificial Analysis Intelligence Index v5.0 59.4 at high, first at the time (Oct 28); Google's own figures: SEC-bench Pro 88.2%, ExploitGym 54.8%, CWE-bench 71.0%; billing SKUs appeared on Google Cloud's SKU list Nov 10, read 08:55 UTC · 16:51 UTC: OpenRouter lists google/gemini-4-carbon at $2 / $10, 1,048,576 context, plus :batch at $1 / $5; Vertex AI's model docs still do not · CursorBench 4.0 (cursor.com/cursorbench, read 16:51 UTC): #1 at 60.4% on high ($9.22 per task) and 60.1% on medium ($8.49), against Fable 5.2 max 60.0% ($32.79) and Opus 5.5 max 57.8% ($13.43); Argon high 52.9% · SimpleBench (read 18:50 UTC Nov 10): 92.6%, #2 behind Fable 5.2 at 94.9%; Argon 91.7%.
Gemini 4 Carbon tops CursorBench 4.0 at 60.4%, edging Claude Fable 5.2 at less than a third of the cost per task
2026-11-10 · Gemini 4 Carbon is #1 on CursorBench 4.0, Cursor's coding-agent benchmark, at 60.4% on its high thinking setting, hours after Google made it generally available. That edges out Claude Fable 5.2 at its max setting, 60.0%, at less than a third of the cost per task by Cursor's figures.
Gemini 4 Carbon is live on the Gemini API at $2 / $10 per 1M tokens until November 30, then $4 / $20
2026-11-10 · Google made Gemini 4 Carbon generally available on the Gemini API on November 10 as gemini-4-carbon, at an introductory $2 per 1M input tokens and $10 per 1M output tokens through November 30. ArtificialWatch's radar fired at 15:46 UTC.
Gemini 4 Argon at a glance
- Developer
- Status
- Live since October 13, 2026
- API price
- $2 input / $10 output per 1M tokens · Google, gemini-4-argon
- Context window
- 1.05M tokens
Live — Oct 13 · GA as gemini-4-argon on the Gemini API (Google changelog), also in AI Studio, Vertex AI, the Gemini app and Antigravity · $2 / $10 per 1M through Nov 30, 2026, then $4 / $20 from Dec 1; cached input $0.10, then $0.20 (implicit caching only) · Batch and Flex half price, Priority $3.60 / $18 · on the API, Google's pricing page says it is not on the Free tier or on the Google AI Pro plan; the consumer Google AI Pro and Ultra subscriptions do include it in the Gemini app (gemini.google, read Oct 15) and in Antigravity's desktop app and CLI since Oct 13 (Google's Antigravity blog), where a screenshot @LuminaBench posted Oct 15 shows a separate weekly Argon limit · 1,048,576-token context shared by input and output; 65,536 max output by default, up to 1,048,576 with long decode · thinking low / medium / high · knowledge cutoff March 2026 (model card) · Google's own table: ahead of Claude Opus 5.5 on 14 of 18 shared rows, behind on FrontierSWE v2 (55.0 vs 62.3), Terminal-Bench 4.0 (57.4 vs 66.4), PostTrainBench and Terminal-Bench Science · Artificial Analysis Intelligence Index (read Oct 13): 52.6 at high, level with GPT-6 Astra (52.7), behind Opus 5.5 (57.6), Sonnet 5.5 (56.0), Muse Wonder Full (55.8) and Fable 5.1 (53.4) · #1 on the Vals Index (68.9%) · ARC Prize, verified (read Oct 15): ARC-AGI-3 97.5% through the provider adapter harness and 49.8% on the standard harness, ARC-AGI-2 91.3% ($0.32 a task), ARC-AGI-1 98.5% · Epoch Capabilities Index (read Oct 15): 164.6, fifth, behind Opus 5.5 (166.8), GPT-6 Astra (166.4), GPT-6.1 Sol (166.3) and Fable 5.1 (164.7), with overlapping confidence intervals · our sweep fired at 15:45 UTC · announced Sep 30 for Fairwind trusted testers first · the newer Gemini 4 checkpoints Business Insider reported Oct 9 file under their own hunts: Carbon (announced Oct 28, gemini-4-carbon) and Barium (gemini-4-next) · Cognition FrontierCode 2.0 (read Oct 30): 26.3% at high in Devin CLI, twelfth of 26, $6.51 a task.
Google doubles seven Gemini API prices: Gemini 4 Argon reaches Claude Opus 5.5's $4 / $20 on December 1, and Gemini 3.8 Flash goes to $1.50 / $7.50 on January 1
2026-11-06 · Google's own pricing pages date a doubling for seven Gemini models, starting with Gemini 4 Argon, which goes from $2 / $10 to $4 / $20 per million input and output tokens on December 1, the same list price as Claude Opus 5.5. Opus 5.5 is first on ArtificialWatch's bench index; Argon is seventh.
Gemini 4 Argon scores 97.5% on ARC-AGI-3 through a provider adapter, 49.8% on the standard harness
2026-10-15 · ARC Prize has published verified scores for Gemini 4 Argon, and on ARC-AGI-3 there are two very different numbers. Run through what ARC Prize calls the provider adapter harness, Argon scores 97.5% at low effort. On ARC Prize's standard harness it scores 49.8%.
Gemini 4 Carbon vs Gemini 4 Argon: quick answers
Which is better, Gemini 4 Carbon or Gemini 4 Argon?
It depends on what you measure. Gemini 4 Carbon scores higher than Gemini 4 Argon on all 4 public leaderboards that rate both. Gemini 4 Carbon's widest lead is on LLM Stats. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Gemini 4 Carbon is at 94.6 and Gemini 4 Argon at 79.7 (out of 100).
Which is newer, Gemini 4 Carbon or Gemini 4 Argon?
Gemini 4 Carbon. It went live on November 10, 2026, 28 days after Gemini 4 Argon (October 13, 2026).
How do Gemini 4 Carbon and Gemini 4 Argon compare for coding?
On the ArtificialWatch coding index, Gemini 4 Carbon is at 91.8 (#2 of 47) and Gemini 4 Argon at 95.2 (#1). Gemini 4 Carbon scores higher on 1 of the 2 coding boards that rate both and Gemini 4 Argon on 1.
Who makes Gemini 4 Carbon and Gemini 4 Argon?
Both are from Google.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed November 10, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear when the next one drops. Free.
Free: a Chrome push and an email about 15 minutes after a new model answers on a public API. Members get a text or a phone call the moment a launch is confirmed.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire