← comparisons · head to head
Claude Fable 5.2 vs Gemini 4 Carbon
Claude Fable 5.2 scores higher than Gemini 4 Carbon on all 5 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Claude Fable 5.2 is at 100 and Gemini 4 Carbon at 93.7 (out of 100). On each maker's API, Claude Fable 5.2 costs $8 / $40 per 1M tokens (input / output) and Gemini 4 Carbon $2 / $10.
Scores as published by each board; table composed November 11, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Claude Fable 5.2 | Gemini 4 Carbon | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,835.8 | 1,768.2 | Claude Fable 5.2 |
| LiveBench global average (0-100) | 84.9 | 83.5 | Claude Fable 5.2 |
| SimpleBench AVG@5 % (private set) | 94.9 | 92.6 | Claude Fable 5.2 |
| LLM Stats LLM Stats Score · composite (0-100), their rendered top 15 | 61.3 | 57.5 | Claude Fable 5.2 |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 71.3 | 70.5 | Claude Fable 5.2 |
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, Claude Fable 5.2 is at 81.5 (#8 of 47) and Gemini 4 Carbon at 100 (#1). Claude Fable 5.2 scores higher on 1 of the 2 coding boards that rate both and Gemini 4 Carbon on 1.
| Coding board | Claude Fable 5.2 | Gemini 4 Carbon |
|---|---|---|
| LiveBench · Coding | 79.2 | 91 |
| Vals Vibe Code Bench | 93.8 | 89.1 |
Claude Fable 5.2 at a glance
- Developer
- Anthropic
- Status
- Live since November 9, 2026
- API price
- $8 input / $40 output per 1M tokens · Anthropic, claude-fable-5-2
- Context window
- 1M tokens
Live — Nov 9 · Anthropic's upgrade of Fable; Mythos 5.2 is the same underlying model without certain cyber and biology safeguards · claude-fable-5-2 on the Claude API, AWS, Google Cloud and Microsoft Azure · $8 / $40 per 1M (Fable 5.1 was $10 / $50); optional fast mode, up to 2.5x faster, $16 / $80 · 1M ctx, 128K max output, adaptive thinking always on, default effort high on the API and medium in Claude apps, reliable knowledge cutoff Jun 2026 (Anthropic's models overview) · Anthropic's own figures: output up to 30% faster than Fable 5.1; FrontierCode 2.0 45.3% at High (Opus 5.5 best 45.5%) for about half the cost per task, 49.1% at Xhigh; BenchCAD 2.1 83.5 (Opus 5.5 65.3); RoboDojo Sim 64.9% (GPT-6 Astra 29.8%) · Artificial Analysis Intelligence Index (read Nov 9 19:55 UTC): Fable 5.2 (Max) 65, ranked first · launch week: eligible paid plans get 1-3 Fable resets, and Pro and standard Team seats can spend up to 50% of weekly usage on Fable · AWS's public price list carried it from 18:09:52 UTC; our sweep first saw claude-fable-5-2 at 18:52:10 UTC and fired at 18:53:06, 4 min 53 s before @claudeai's post · Epoch Capabilities Index (eci_scores.csv, updated Nov 9, read 21:52 UTC): 174.24 (CI 170.12-178.79), ranked first of 255, ahead of GPT-6 Astra 169.16; Fable 5.1 167.04 · SemiAnalysis GDPx (read 01:50 UTC Nov 10): 16.4%, first, ahead of Opus 5.5 12.0% and Fable 5.1 8.5%; $88.15 per task and 1.23M output tokens per task, the most of any model listed · Nov 10: Remote Labor Index (Center for AI Safety and Scale AI, Scale's leaderboard read 14:50 UTC): 41.3%, #1, against Opus 5.5 21.25%, GPT-6 Astra 20.83%, Fable 5.1 17.92% and Gemini 4 Argon 17.08% · SimpleBench (simple-bench.com leaderboard data, read 18:50 UTC Nov 10): 94.9% AVG@5, #1, half a point below the highest human score of 95.4%, ahead of Gemini 4 Carbon 92.6% and Argon 91.7%.
Claude Fable 5.2 tops SimpleBench at 94.9%, half a point below the best human score, with Gemini 4 Carbon second at 92.6%
2026-11-10 · Claude Fable 5.2 is #1 on SimpleBench at 94.9%, half a point below the highest human score the benchmark records, 95.4%. SimpleBench's leaderboard data, read by ArtificialWatch at 18:50 UTC on November 10, added Fable 5.2 and both Gemini 4 models that day. @Mr_Salio flagged the update at 18:03 UTC.
Claude Fable 5.2 tops the Remote Labor Index at 41.3%, nearly double the next model
2026-11-10 · Claude Fable 5.2 is #1 on the Remote Labor Index, fully automating 41.3% of its projects. That is nearly double the next model, Claude Opus 5.5, at 21.25%. ArtificialWatch read the scores on Scale AI's public leaderboard at 14:50 UTC on November 10.
Gemini 4 Carbon at a glance
- Developer
- Status
- Live since November 10, 2026
- API price
- $2 input / $10 output per 1M tokens · Google, gemini-4-carbon
- Context window
- 1.05M tokens
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.
Claude Fable 5.2 vs Gemini 4 Carbon: quick answers
Which is better, Claude Fable 5.2 or Gemini 4 Carbon?
It depends on what you measure. Claude Fable 5.2 scores higher than Gemini 4 Carbon on all 5 public leaderboards that rate both. Claude Fable 5.2'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, Claude Fable 5.2 is at 100 and Gemini 4 Carbon at 93.7 (out of 100).
Which is newer, Claude Fable 5.2 or Gemini 4 Carbon?
Gemini 4 Carbon. It went live on November 10, 2026, 1 day after Claude Fable 5.2 (November 9, 2026).
Which is cheaper, Claude Fable 5.2 or Gemini 4 Carbon?
Gemini 4 Carbon is cheaper on both input and output. On each vendor's own API, Claude Fable 5.2 is $8 input / $40 output per million tokens and Gemini 4 Carbon is $2 input / $10 output per million tokens. Prices as published in the models.dev catalog, as of 2026-11-11.
Which has the bigger context window, Claude Fable 5.2 or Gemini 4 Carbon?
Gemini 4 Carbon, at 1.05M tokens against Claude Fable 5.2's 1M, as each vendor lists it.
How do Claude Fable 5.2 and Gemini 4 Carbon compare for coding?
On the ArtificialWatch coding index, Claude Fable 5.2 is at 81.5 (#8 of 47) and Gemini 4 Carbon at 100 (#1). Claude Fable 5.2 scores higher on 1 of the 2 coding boards that rate both and Gemini 4 Carbon on 1.
Who makes Claude Fable 5.2 and Gemini 4 Carbon?
Claude Fable 5.2 is from Anthropic; Gemini 4 Carbon is from Google.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed November 11, 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 · what a workload costs on each · the wire