Frontier AI Models Compared: Fable 5.2 vs GPT-6, Gemini 4, Grok 4.7 and Open Weights

Claude Fable 5.2 holds the top independent score at 65 on Artificial Analysis's Intelligence Index as of November 9, 2026, ahead of Gemini 4 Carbon at 59, Claude Opus 5.5 at 58 and GPT-6 Astra at 57, according to a comparison of eleven frontier and near-frontier models. Anthropic's Fable 5.2 lists at $8 per million input and $40 per million output tokens, while Grok 4.7 is the cheapest closed model at $2/$6 and DeepSeek V4.1 Flash 1017 the cheapest open-weight model at $0.15/$0.60 off-peak under an MIT license. Google's Gemini 4 Carbon has no public ID and is available only to selected cyber defenders, and the comparison cautions that most coding numbers are lab-run on different harnesses and effort settings.

Claude Fable 5.2 now leads the independent leaderboard, but "best model" depends on whether you mean the highest score, the lowest bill, or the one you can actually call today. In the two weeks around November 9, 2026, Anthropic shipped Fable 5.2 https://explainx.ai/blog/claude-fable-5-2-mythos-5-2-launch-pricing-api-2026 , Google announced Gemini 4 Carbon, Moonshot opened the weights of Kimi K3.1 Pro, and Tencent released Hy4. This post puts eleven frontier and near-frontier models in one frame: Anthropic, OpenAI, Google, SpaceXAI Grok and the open-weight labs. We use independent scores first, lab-reported numbers second, then price, access and license. We flag every place where the numbers do not compare, because a surprising amount of cross-lab benchmarking is apples to oranges. For the Claude-only deep dive, read Fable 5.2 vs Opus 5.5 https://explainx.ai/blog/claude-fable-5-2-vs-opus-5-5-benchmarks-cost-routing-which-model-2026 . TL;DR: the questions people ask first | Question | Direct answer | |---|---| | Highest independent score? | Claude Fable 5.2 at 65 Artificial Analysis, Nov 9 . On the v5 index: Carbon 59, Opus 5.5 58, GPT-6 Astra 57 | | Cheapest closed model? | Grok 4.7: $2 / $6 per million tokens. GPT-6.1 Sol: $2 / $10 | | Cheapest open weights? | DeepSeek V4.1 Flash 1017: $0.15 / $0.60 off-peak, MIT license | | Best open-weight model? | Kimi K3.1 Pro: 46 on v5, 65.7% Terminal-Bench 4.0 self-reported , 2.8T parameters | | Can I call Gemini 4 Carbon? | No public ID. Selected cyber defenders only | | Priciest? | GPT-6 Astra $10 / $50, then Fable 5.2 $8 / $40 | | Biggest caveat? | Most coding numbers are lab-run, on different harnesses and effort settings | The master table: eleven models, one view Scores come from different sources, so the source is part of the number. "AA v5" is Artificial Analysis's Intelligence Index v5. Prices are list prices per million input and output tokens. | Model | Lab | Price in / out | Independent score | Access today | Weights | |---|---|---|---|---|---| | Claude Fable 5.2 | Anthropic | $8 / $40 | 65 AA, Nov 9 | API, AWS, Google Cloud, Azure | Closed | | Gemini 4 Carbon | Google DeepMind | $4 / $20 $2 / $10 intro | 59 AA v5 | Selected cyber defenders only | Closed | | Claude Opus 5.5 | Anthropic | $4 / $20 | 58 AA v5 | API, Claude apps | Closed | | GPT-6 Astra | OpenAI | $10 / $50 | 57 AA v5 | ChatGPT, API | Closed | | GPT-6.1 Sol | OpenAI | $2 / $10 | 55 AA v5 | All paid plans, API | Closed | | Gemini 4 Argon | Google DeepMind | $2 / $10 intro see launch post | 50 AA v5 | Generally available after a Fairwind-first launch | Closed | | Kimi K3.1 Pro | Moonshot | $2 / $10 | 46 AA v5 | Kimi API, Hugging Face | Open, modified MIT | | Grok 4.7 | SpaceXAI | $2 / $6 | not on AA v5 top list | API, Amazon Bedrock | Closed | | DeepSeek V4.1 Flash 1017 | DeepSeek | $0.15 / $0.60 off-peak | 32 AA v5 | API, web, weights | Open, MIT | | GLM-5.3 | Z.ai | see launch post | 32 AA v5 | API | Open | | Tencent Hy4 | Tencent | RMB 6 / RMB 18 | none yet | TokenHub, OpenRouter | Planned, not released | A podium of ranked AI models, illustrating the frontier model comparison between Fable 5.2 and rivals Three footnotes keep this honest. The Fable 5.2 score of 65 comes from Artificial Analysis's page as we cited it on November 9, and we have not re-run it. Kimi K3.1 Pro was listed on v5 on October 27 as "weights not released"; the weights landed on November 4, so check the current label. Grok 4.7 does not appear in our v5 source table, so we show it without an independent score rather than guess. How does Fable 5.2 stack up against GPT-6 Astra and Gemini 4 Carbon? Anthropic's launch post is the only table that puts Fable 5.2, GPT-6 Astra and Gemini 4 Carbon on the same rows. It is Anthropic's table, so every row favors Anthropic's chosen benchmarks, but it is the best three-way data we have. Opus 5.5 is included as a reference. | Benchmark | Fable 5.2 | Opus 5.5 | GPT-6 Astra | Gemini 4 Carbon | |---|---|---|---|---| | FrontierCode 2.0 agentic coding | 49.1% | 45.5% | 42.8% | 41.1% | | FrontierSWE v2 agentic coding | 69.9% | 62.3% | 65.5% | 61.2% | | AutomationBench business workflows | 51.4% | 42.5% | 41.4% | 53.9% | | Terminal-Bench-Science 0.1 | 74.6% | 58.7% | 68.1% | 64.8% | | OSWorld 2.1 computer use | 89.3% | 87.2% | 79.5% | 81.5% | | RoboDojo Sim robotics | 64.9% | 39.4% | 29.8% | not reported | | Remote Labor Index High effort | 41.3% | 21.3% | 20.8% | not reported | | Humanity's Last Exam tools | 74.2% | 67.7% | 57.2% | not reported | | Chartography no tools | 73.4% | 64.4% | 71.0% | 72.5% | Fable 5.2 wins eight of nine rows here. Carbon wins AutomationBench, and its Chartography score of 72.5% is within one point. Astra is second on FrontierSWE v2 and Terminal-Bench-Science. The pattern matches what independent boards showed for Carbon earlier: it is strong on broad composites and weaker where long tool-heavy agents are involved. Our Carbon vs Opus 5.5 vs Astra vs Grok 4.7 post https://explainx.ai/blog/gemini-4-carbon-vs-claude-opus-5-5-vs-gpt-6-astra-vs-grok-4-7-comparison-2026 has the independent view. Two practical limits. First, Anthropic omits benchmarks it does not win, so absence is information. Second, Carbon is not callable by the public, which means a Fable 5.2 vs Carbon bake-off is a thought experiment for most readers today. See the Carbon launch coverage https://explainx.ai/blog/gemini-4-carbon-launch-cyber-defenders-first-59-intelligence-index-pricing-2026 for how access is expanding. What does each frontier model cost? A bead diverted at a three-way pipe junction, a picture of routing work across frontier models by price List prices span almost two orders of magnitude, from DeepSeek at $0.15 input to GPT-6 Astra at $10. | Tier | Models | Input / output per 1M | |---|---|---| | Premium | GPT-6 Astra; Claude Fable 5.2 | $10 / $50; $8 / $40 | | Mid | Claude Opus 5.5; Gemini 4 Carbon standard | $4 / $20 | | Value | GPT-6.1 Sol; Kimi K3.1 Pro | $2 / $10 | | Cheap | Grok 4.7 | $2 / $6 | | Very cheap | DeepSeek V4.1 Flash 1017 | $0.15 / $0.60 off-peak doubles at peak | List price is not cost per task. In Artificial Analysis's v5 run, one Index task cost about $10.04 on Opus 5.5 max , $7.76 on Carbon, $6.24 on GPT-6 Astra and $1.27 on GPT-6.1 Sol. Astra costs five times Sol per token and about five times per task $6.24 against $1.27 . We did not find a published Fable 5.2 per-task figure on that board, and Anthropic's own cost claims are matched-effort comparisons against Opus 5.5. The practical rule is the same for every row: price a successful artifact , not a million tokens. Our Sol vs Astra cost note https://explainx.ai/blog/gpt-6-1-sol-astra-cost-efficiency-2026 and the output-token inflation post https://explainx.ai/blog/ai-labs-output-token-inflation-pricing-playcode-2026 explain how a cheaper token can still produce a bigger bill. Where does GPT-6.1 Sol beat the premium tier? GPT-6.1 Sol is the model to beat on value. OpenAI sells it at $2 / $10, one-fifth of Astra's standard rates, with a 95% cache-read discount $0.10 per million cached input , and Artificial Analysis scores it at 55 versus Astra's 57. If your agent loop is cache-friendly and your tasks sit inside what Sol handles, that is a large saving for a two-point drop. The GPT-6.1 Sol launch coverage https://explainx.ai/blog/gpt-6-1-sol-launch-pricing-benchmarks-2026 lists what to rerun before you move. Fable 5.2 does not compete on price. It competes on the hardest long-horizon rows, where it leads Astra by 20 points on Remote Labor Index and 35 on RoboDojo. If your work does not look like those rows, Sol or Opus 5.5 is a saner default. Is Grok 4.7 still a frontier model? Grok 4.7 is the cheap live option, but it is not the leader. SpaceXAI shipped it on September 21, 2026 at $2 / $6, the same price as Grok 4.6, and our launch breakdown https://explainx.ai/blog/grok-4-7-launch-benchmarks-pricing-2026 shows it winning EEBench and a legal-agent benchmark while trailing Fable 5.1 on CursorBench 4.0 and Terminal-Bench 4.0 38.0% against 57.9% . That Terminal-Bench 4.0 gap is the clearest cross-lab number. Opus 5.5 posted 66.4%, GPT-6 Sol 43% an Artificial Analysis run and Grok 4.7 38.0%; see our Grok 4.7 vs Opus 5.5 vs GPT-6 Sol comparison https://explainx.ai/blog/grok-4-7-vs-opus-5-5-vs-gpt-6-sol-comparison-2026 . Grok 4.7 is also on Amazon Bedrock. We did not find a Grok newer than 4.7 in released form as of this post, so treat Grok as the price floor among closed models, not the performance ceiling. How close are open-weight models to the frontier? Two rows of server blocks, one open and one closed, showing open-weight versus closed frontier models Closer on some benchmarks, far on others. Three data points frame it. Kimi K3.1 Pro Moonshot . Released October 23 with weights on Hugging Face on November 4. It is a mixture-of-experts model with 2.8T total parameters, 104B active, 896 experts and a 1M-token context. Moonshot self-reports 65.7% on Terminal-Bench 4.0, against 66.4% for Opus 5.5 and 58.2% for GPT-6 Astra in Moonshot's own table. Artificial Analysis scored it 46 on v5, which is 12 points below Opus 5.5 and well above the other open weights. API price is $2 / $10. The license is MIT-style with conditions: a Model-as-a-Service business earning over $20 million in any 12 months must sign a separate agreement, and products with over 100 million monthly users or $20 million monthly revenue must show attribution. Full detail is in our Kimi K3.1 Pro post https://explainx.ai/blog/kimi-k3-1-pro-open-weights-benchmarks-price-terminal-bench-nov-4-2026 . DeepSeek V4.1 Flash 1017. MIT-licensed, about 763B parameters, 1M context, and $0.15 / $0.60 off-peak. DeepSeek self-reports Terminal-Bench 4.0 rising from 31.2 to 42.3 in one point release, and Artificial Analysis scored it 32 on v5. That is slightly above Grok 4.7's 38.0% on the same benchmark at a fraction of the price. DeepSeek ran the Claude Code harness for that number, which matters, because harness choice moves agent scores. See the DeepSeek V4.1 Flash 1017 post https://explainx.ai/blog/deepseek-v4-1-flash-1017-open-weights-mit-terminal-bench-4-42-benchmarks-pricing-2026 . Tencent Hy4 and others. Hy4 is a 770B MoE with vision and computer use, released November 4. Tencent's own tests rank it second to fourth of seven, and the final weights are planned but not released our Hy4 post https://explainx.ai/blog/tencent-hy4-official-release-770b-vision-computer-use-terminal-bench-44-4-weights-planned-2026 . A Qwen Code commit treats qwen4 as a 1M-token family, but the launch itself is unconfirmed claimed vs verified https://explainx.ai/blog/qwen4-qwen-code-commit-1m-context-default-qwen4-coder-plus-omni-120b-think-claimed-vs-verified-2026 . Smaller entrants such as Ripple-65B report strong self-run scores that nobody has reproduced yet claimed vs verified https://explainx.ai/blog/ricursive-ripple-65b-preview-dense-open-weight-model-terminal-bench-80-5-apache-claimed-vs-verified-2026 . The honest summary: on agentic coding as one vendor measures it, open weights are within one point of Opus 5.5. On the independent composite, they are 12 to 26 points below the leaders. Both statements are true, because the benchmark choice decides the answer. Which model should I use for what? | If you need | Start with | Why | |---|---|---| | The hardest long-horizon agent work | Claude Fable 5.2 | Largest published leads on Remote Labor Index, WANDR and RoboDojo | | A default coding agent at a mid price | Claude Opus 5.5 | Ties Fable on FrontierCode at half the list price; leads Coding Agent Index in Artificial Analysis | | Best value from a US closed lab | GPT-6.1 Sol | $2 / $10, 95% cache discount, 55 on AA v5 | | Lowest closed-model price | Grok 4.7 | $2 / $6, live on Bedrock | | Self-hosting and data control | Kimi K3.1 Pro | Open weights, strong self-reported agentic coding, license limits for big resellers | | Bulk, cost-sensitive volume | DeepSeek V4.1 Flash 1017 | MIT, $0.15 / $0.60 off-peak | | Cyber defense research | Wait for Carbon access | Google targets selected defenders first | Two dials for cost and power, a picture of choosing between frontier models by budget A routing setup beats a single pick. A common pattern is a premium model for planning and a value model for execution: Fable 5.2 plans, Opus 5.5 or Sol executes, DeepSeek handles bulk classification. Our Fable 5.2 vs Opus 5.5 routing sketch https://explainx.ai/blog/claude-fable-5-2-vs-opus-5-5-benchmarks-cost-routing-which-model-2026 shows one way to code it. Why you cannot trust a single leaderboard Four traps recur in cross-lab comparisons, and each shows up in the tables above. 1. Different harnesses. DeepSeek used the Claude Code harness for Terminal-Bench 4.0. Carbon ran in Antigravity CLI on Artificial Analysis. A model can rank first in one harness and second in another, as Carbon did against Opus 5.5. 2. Different effort settings. Fable 5.2 is reported at Xhigh or Max on some rows and Medium on others. Comparing a Max row against a competitor's default is not a fair test. 3. Different index versions. Kimi K3.1 Pro scored 55 on the Artificial Analysis index at launch on October 23 and 46 on v5 four days later. The rebuild changed the weights, so scores from different versions are not comparable. 4. Self-selected comparisons. Each lab picks its own rivals. Anthropic's table omits benchmarks it does not win. Moonshot's table compares against Opus 5.5 and Astra on its chosen rows. Our guide on how to read AI benchmarks https://explainx.ai/blog/how-to-read-ai-benchmarks goes through these in more depth, and the Artificial Analysis v5 write-up https://explainx.ai/blog/artificial-analysis-intelligence-index-v5-opus-5-5-58-private-benchmarks-open-weight-gap-12-points-2026 explains why about 60% of that index uses private or held-out data. Honest limitations - We did not run these models. Every score is cited from the lab or an evaluator, and we have not reproduced any of them. - Fable 5.2's 65 on Artificial Analysis is as reported in our November 9 coverage; index weights change between versions. - Anthropic's three-way table is Anthropic's. Rows for GPT-6 Astra and Gemini 4 Carbon were run or reported by Anthropic, and one chart labels the Gemini model differently from the table. - Gemini 4 Carbon is not publicly available. Its numbers cannot be checked by most readers. - Missing data. Fable 5.2 has no published Terminal-Bench 4.0 or per-task cost on the board we cited, and Tencent Hy4 has no independent evaluation. - Prices change quickly. Introductory rates, off-peak discounts and cache tiers all move the real bill. - Open-weight license terms are summarized from the model cards. Read the license before you ship a commercial product. What this means for what you build or pay If you pay for frontier tokens today, the biggest lever is not picking the top-scoring model. It is routing. Most teams can send planning, search and ambiguous long runs to Fable 5.2, send routine coding to Opus 5.5 or GPT-6.1 Sol, and send bulk work to DeepSeek or a self-hosted Kimi, then measure cost per solved task. If you care about data control, Kimi K3.1 Pro and DeepSeek V4.1 Flash 1017 are the first open-weight options that agent builders can plausibly use in production, with the license and hardware caveats above. If you need the highest ceiling, Fable 5.2 leads on the numbers we can see. Run your own 20 to 50 tasks through two or three candidates before you commit. Related on explainx.ai Primary sources: Anthropic's Fable 5.2 announcement https://www.anthropic.com/claude-fable-and-mythos-5-2?ref=explainx , Moonshot's Kimi K3.1 Pro model card on Hugging Face https://huggingface.co/moonshotai/Kimi-K3.1-Pro?ref=explainx , DeepSeek V4.1 Flash 1017 model card https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017?ref=explainx , Artificial Analysis Intelligence Index v5 https://artificialanalysis.ai/articles/artificial-analysis-intelligence-index-v5?ref=explainx . Scores, prices and access status are accurate as of November 10, 2026. Frontier model releases change weekly, so re-check each provider's pricing page before you build on this table.