BlogLLM Benchmark Scores as Published, Side by Side

Claude Fable 5.2 vs Grok 4.7: Benchmark Scores Side by Side

Every test both Claude Fable 5.2 by Anthropic and Grok 4.7 by xAI have a published number for: 11 tests in 4 areas. Each number is as printed, with the page it comes from and the setup it was run under; nothing is ranked or rescored, and two numbers under different setups are two results, not one comparison.

Models Claude Fable 5.2, Grok 4.7Data version 2026111201, as of 2026-11-12

Model

What each developer prints on its own model page; a dash means it prints none.

FactClaude Fable 5.2Grok 4.7
Released2026-11-092026-09-21
Context window1M500K
Max output128K-
InputText, imageText, image
OutputTextText
WeightsClosedClosed

Knowledge Work

TestClaude Fable 5.2Grok 4.7
GDPval-AA v2.1
1695xAI, Grok 4.7, checked 2026-10-25Effort: xhigh
AA-Briefcase v1.1
1785Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
1657xAI, Grok 4.7, checked 2026-10-25Effort: xhigh

Agentic Coding

TestClaude Fable 5.2Grok 4.7
DeepSWE v1.1
71%xAI, Grok 4.7, checked 2026-10-25; printed on 1 more pageEffort: high
Terminal-Bench 4.0
67.6%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Claude Code --bare; Fallback: safeguards on; the fallback answered 2.5% of requests, affecting 10% of trials
37.6%xAI, Grok 4.7, checked 2026-10-25; printed on 1 more pageEffort: xhigh
FrontierSWE v2
69.9%Anthropic, Claude Fable 5.2 and Mythos 5.2, checked 2026-11-09; printed on 1 more page
29%xAI, Grok 4.7 model card, checked 2026-10-14Effort: xhigh
Vibe Code Bench
93.77%Vals AI, Vibe Code Bench v1.1 leaderboard, checked 2026-11-09Harness: OpenHands
86.17%Vals AI, Vibe Code Bench v1.1 leaderboard, checked 2026-11-02Harness: OpenHands
CursorBench 4.0
60%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: max; Harness: Cursor production harness
54.8%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: medium; Harness: Cursor production harness
53.2%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: low; Harness: Cursor production harness
56.9%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: high; Harness: Cursor production harness
56.3%Anthropic, System Card: Claude Fable 5.2 & Claude Mythos 5.2, checked 2026-11-09Effort: xhigh; Harness: Cursor production harness
41.6%xAI, Grok 4.7, checked 2026-10-25; printed on 1 more pageEffort: medium
33.1%xAI, Grok 4.7, checked 2026-10-25Effort: low
43.9%xAI, Grok 4.7, checked 2026-10-25Effort: high
46.3%xAI, Grok 4.7, checked 2026-10-25Effort: xhigh

Science and Math

TestClaude Fable 5.2Grok 4.7
GPQA Diamond
93.9%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max
92.7%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-10-30Effort: xhigh
FrontierMath Tier 4 (v2)
100%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max
17.1%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-10-30Effort: xhigh
FrontierMath Tier 1-3 (v2)
95.1%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max
53%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-10-30Effort: xhigh

General Knowledge and Reasoning

TestClaude Fable 5.2Grok 4.7
SimpleQA Verified
94%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-11-10Effort: max
56%Epoch AI, Epoch AI Benchmarking Hub, checked 2026-10-30Effort: xhigh

Price

API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked; a dash means the developer lists that price in another unit or not at all. Cost per task is measured by Vals AI.

PriceClaude Fable 5.2Grok 4.7
Input
$8Anthropic, Anthropic API pricing, checked 2026-11-09
$2xAI, xAI API pricing, checked 2026-10-15Context: up to 200,000 tokens; Long context: $4 per 1M tokens above 200,000 tokens
Cached input
$0.2Anthropic, Anthropic API pricing, checked 2026-11-09
$0.5xAI, xAI API pricing, checked 2026-10-15Context: up to 200,000 tokens; Long context: $1 per 1M tokens above 200,000 tokens
Cache write
$10Anthropic, Anthropic API pricing, checked 2026-11-09Cache: 5 minute cache
-
Cache write, 1 hour
$16Anthropic, Anthropic API pricing, checked 2026-11-09
-
Output
$40Anthropic, Anthropic API pricing, checked 2026-11-09
$6xAI, xAI API pricing, checked 2026-10-15Context: up to 200,000 tokens; Long context: $12 per 1M tokens above 200,000 tokens
Input, batch
$4Anthropic, Anthropic API pricing, checked 2026-11-09
-
Output, batch
$20Anthropic, Anthropic API pricing, checked 2026-11-09
-
Input, fast
$16Anthropic, Anthropic API pricing, checked 2026-11-09
$4xAI, xAI API pricing, checked 2026-10-15Context: up to 200,000 tokens; Long context: $6 per 1M tokens above 200,000 tokens
Cached input, fast-
$1xAI, xAI API pricing, checked 2026-10-15Context: up to 200,000 tokens; Long context: $1.5 per 1M tokens above 200,000 tokens
Output, fast
$80Anthropic, Anthropic API pricing, checked 2026-11-09
$12xAI, xAI API pricing, checked 2026-10-15Context: up to 200,000 tokens; Long context: $18 per 1M tokens above 200,000 tokens
Cost per taskVals AI, USD, lower is better
$22.13Vals AI, Vibe Code Bench v1.1 leaderboard, checked 2026-11-09Harness: OpenHands
$15.83Vals AI, Vibe Code Bench v1.1 leaderboard, checked 2026-10-27Harness: OpenHands

Claude Fable 5.2 has 35 more and Grok 4.7 has 37 more: tests only one of them has a number for, listed on its model page.

More side by side

Every number here is read from the same catalog file as the benchmark table, data version 2026111201. A pair has a page when both models are their developers' flagships and both have a number for at least 10 of the same tests. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.