Frontier comparison · July 2026

GPT‑5.6 Sol vs Claude Fable 5

Sol is cheaper and stronger on published agentic-coding and long-horizon professional results. Fable leads on repo-level SWE‑bench Pro, aggregate intelligence, difficult math, and parts of knowledge work. This is a real split frontier—not a single-score race.

Last updated July 10, 2026 · Published scores, source caveats, no invented rows

OpenAI flagship

GPT‑5.6 Sol

$5 / $30
Input / output per 1M · 1.05M context · 128K output · max and ultra modes
Anthropic flagship

Claude Fable 5

$10 / $50
Input / output per 1M · 1M context · 128K output · always-on adaptive thinking
Short version: Sol is the value leader for tool-using coding agents: it is half the price on input, 40% cheaper on output, and leads the published Coding Agent Index and Terminal‑Bench 2.1. Fable has the stronger published SWE‑bench Pro result and the higher Artificial Analysis Intelligence Index. Your choice should follow the task shape: terminal execution and professional agent work favor Sol; repository issue resolution and peak analytical quality favor Fable.

Token economics: Sol costs materially less

Fable is the more expensive model before performance enters the picture. Sol’s input price is half Fable’s, its output price is 40% lower, and its cache reads are half the price. Fable’s advantage is that Anthropic documents standard pricing across its full 1M-token context window; Sol adds a surcharge when input exceeds 272K tokens.

API propertyGPT‑5.6 SolClaude Fable 5
Input / 1M tokens$5.00$10.00
Output / 1M tokens$30.00$50.00
Cached input / 1M$0.50$1.00
Cache write / 1M$6.25$12.50 for 5-minute cache; $20 for 1-hour cache
Batch input / output$2.50 / $15.00$5.00 / $25.00
Context / max output1.05M / 128K tokens1M / 128K tokens
Long-context policyOver 272K input: 2× input and 1.5× output for full request1M context at standard pricing
Model accessChatGPT, Codex, and OpenAI APIClaude API, Claude Code, Claude, AWS, Google Cloud, Microsoft Foundry
Illustrative 10M-input + 1M-output workload
Fresh-token arithmetic only. This does not include reasoning tokens, tool charges, or long-context pricing adjustments.
GPT‑5.6 Sol
$80
Claude Fable 5
$150

The published split: coding is not one category

OpenAI’s launch table offers the clearest direct comparison. It shows Sol ahead on the Artificial Analysis Coding Agent Index, DeepSWE, and Terminal‑Bench. Fable is dramatically ahead on SWE‑bench Pro. Those evaluations test different things: terminal-driven task completion and long-horizon engineering versus fixing real repository issues. Treat each score as a task-specific signal, and note that the comparison table is vendor-published.

Coding & agent evaluationGPT‑5.6 SolClaude Fable 5Published edge
Artificial Analysis Coding Agent Index v1.180.077.2Sol +2.8
SWE‑bench Pro64.6%80.0%Fable +15.4 pts
DeepSWE v1.172.7%69.7%Sol +3.0 pts
Terminal‑Bench 2.188.8%83.1%Sol +5.7 pts
Artificial Analysis Intelligence Index v4.158.959.9Fable +1.0
Coding-agent work higher is better; native scales retained
The graph intentionally keeps the separate metrics separate. It is not an overall score.
AA Coding Index · Sol
80.0
AA Coding Index · Fable
77.2
DeepSWE · Sol
72.7%
DeepSWE · Fable
69.7%
Terminal‑Bench · Sol
88.8%
Terminal‑Bench · Fable
83.1%
SWE‑bench Pro · Sol
64.6%
SWE‑bench Pro · Fable
80.0%

Professional work: near tie overall, different strengths

The aggregate intelligence picture is close: Artificial Analysis lists Fable at 60 and Sol at 59 at their respective high-effort settings. But the published sub-benchmarks split. Sol leads the OpenAI table’s long-horizon professional workflow and browsing rows; Fable leads GDPval‑AA and HealthBench Professional by narrow margins.

Professional & computer use

EvaluationSolFable
Agents’ Last Exam52.7%40.5%
GDPval‑AA v21,747.8 Elo1,759.6 Elo
Management consulting tasks43.2%35.5%
BrowseComp90.4%84.3%
OSWorld 2.062.6%54.8%

Academic & health

EvaluationSolFable
HealthBench Professional60.5%60.9%
GPQA Diamond94.6%92.6%
FrontierMath Tier 1–389.0%87.0%
FrontierMath Tier 483.0%87.8%
AutomationBench18.1%17.4%

Tool orchestration and safety behavior

MCP Atlas: Fable has a published 83.3% MCP Atlas result in Anthropic’s system-card configuration. OpenAI has not published an MCP Atlas score for Sol. The absence of a Sol score is not evidence of poor performance; it is simply not a row we can honestly compare.

Safeguards: Anthropic describes Fable as Mythos-class with always-on adaptive thinking and safety handling for high-risk requests. OpenAI describes Sol’s layered real-time safeguards and differentiated access controls. Do not assume equal refusal behavior or latency from benchmark results—test your own legitimate workflows.
Tool / operational dimensionSolFable
MCP AtlasNot published83.3% Anthropic configuration
Toolathlon58.0%61.7%
Context pricingSurcharge over 272K input tokensFull 1M context at standard pricing
Reasoning styleConfigurable, including max; ultra coordinates subagentsAlways-on adaptive thinking

Radar: different peaks, not a single winner

Terminal agentsSWE‑ProMCP evidenceCost efficiencyIntelligence
How to read this radar

The five axes are transparent task dimensions above, not a weighted “best model” score. Fable’s MCP evidence uses its published result; Sol’s missing MCP Atlas row is shown as missing rather than estimated. Cost efficiency is inverted so cheaper extends further.

● GPT‑5.6 Sol   ● Claude Fable 5

  • Sol’s larger terminal and cost axes are meaningful for agent workflows with many tool turns.
  • Fable’s SWE‑bench Pro result is large enough to matter for repo issue-resolution work.
  • The one-point aggregate-intelligence gap is too close to be a safe procurement tie-breaker alone.

What independent measurement adds

Artificial Analysis reports Sol at 59 versus Fable at 60 on its Intelligence Index at high effort. At the same time, it reports Sol leading the Coding Agent Index at 80, ahead of Fable’s 77.2, and estimates Sol’s Intelligence Index task cost at $1.04—about one-third of Fable’s. Its commentary is especially useful because it does not collapse this into a sweep: Fable leads its overall intelligence leaderboard, while Sol leads its coding-agent index.

Decision guide

Choose Sol when…

You build terminal-driven or tool-heavy coding agents, care about the published Coding Agent Index / DeepSWE / Terminal‑Bench leads, want lower token economics, or need configurable max and multi-agent-style ultra workflows.

Choose Fable when…

Your priority is real repository issue resolution, especially if SWE‑bench Pro matches your task style; you need the published MCP Atlas result; or Fable’s 1M standard-priced context and adaptive-thinking behavior fit your stack.

Evaluate both when…

You are selecting a flagship for production. Run held-out repository issues, terminal tasks, long-context documents, and tool chains. Measure successful task cost, retries, tool failures, latency, merge acceptance, and human-review load.

Verdict

Sol is the more economical agentic-engineering flagship. It is materially cheaper, publishes stronger terminal and coding-agent results, and leads long-horizon professional workflow rows in OpenAI’s table. Fable remains the stronger repository-resolution and aggregate-intelligence bet on published evidence. Its SWE‑bench Pro lead is decisive, it edges Sol on the Artificial Analysis Intelligence Index, and it has a published MCP Atlas result.

The honest conclusion is a split frontier. Use Sol where agent execution, tool loops, and cost per run dominate. Use Fable where issue resolution, deep analysis, and standard-priced long context dominate. The best implementation is often a router with a real evaluation set—not a permanent ideological commitment to one frontier model.

Sources & methodology