Compare · ModelsLive · 2 picked · head to head
Claude Opus 4.6 vs Grok 4.6
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Grok 4.6 wins on 13/18 benchmarks
Grok 4.6 wins 13 of 18 shared benchmarks. Leads in agentic · knowledge · general.
Category leads
agentic·Grok 4.6reasoning·Claude Opus 4.6knowledge·Grok 4.6general·Grok 4.6coding·Grok 4.6math·Grok 4.6
Hype vs Reality
Attention vs performance
Claude Opus 4.6
#136 by perf·#9 by attention
Grok 4.6
#62 by perf·#15 by attention
Best value
Grok 4.6
4.5x better value than Claude Opus 4.6
Claude Opus 4.6
3.2 pts/$
$15.00/M
Grok 4.6
14.4 pts/$
$4.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
xAI
$250.0B·Tier 1
Head to head
18 benchmarks · 2 models
Claude Opus 4.6Grok 4.6
APEX-Agents
Grok 4.6 leads by +19.0
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Opus 4.6
46.3
Grok 4.6
65.3
ARC-AGI
Claude Opus 4.6 leads by +6.5
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Opus 4.6
94.0
Grok 4.6
87.5
ARC-AGI-2
Claude Opus 4.6 leads by +2.1
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Opus 4.6
69.2
Grok 4.6
67.1
Chess Puzzles
Grok 4.6 leads by +24.2
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Opus 4.6
12.7
Grok 4.6
36.9
Dtbench
Grok 4.6 leads by +10.2
Claude Opus 4.6
85.3
Grok 4.6
95.5
Ebr Bench
Grok 4.6 leads by +17.8
Claude Opus 4.6
12.7
Grok 4.6
30.5
Frontiercode
Grok 4.6 leads by +21.4
Claude Opus 4.6
26.6
Grok 4.6
48.0
FrontierMath-Tier-4-v2-Private
Grok 4.6 leads by +4.9
Claude Opus 4.6
26.8
Grok 4.6
31.7
FrontierMath-Tiers-1-3-v2-Private
Claude Opus 4.6
66.0
Grok 4.6
66.0
Furniture Assembly
Grok 4.6 leads by +14.3
Claude Opus 4.6
0.0
Grok 4.6
14.3
GPQA diamond
Grok 4.6 leads by +4.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 4.6
87.4
Grok 4.6
92.0
Lmca
Claude Opus 4.6 leads by +8.6
Claude Opus 4.6
65.6
Grok 4.6
57.0
Mystery Game Puzzles
Grok 4.6 leads by +9.9
Claude Opus 4.6
17.4
Grok 4.6
27.3
OTIS Mock AIME 2024-2025
Grok 4.6 leads by +4.7
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 4.6
94.4
Grok 4.6
99.2
Proofbench
Grok 4.6 leads by +1.0
Claude Opus 4.6
50.0
Grok 4.6
51.0
SimpleBench
Grok 4.6 leads by +10.0
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Opus 4.6
61.1
Grok 4.6
71.1
SimpleQA Verified
Grok 4.6 leads by +2.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Opus 4.6
47.0
Grok 4.6
49.3
WeirdML
Claude Opus 4.6 leads by +10.7
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Opus 4.6
78.0
Grok 4.6
67.3
Full benchmark table
| Benchmark | Claude Opus 4.6 | Grok 4.6 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 46.3 | 65.3 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 94.0 | 87.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 69.2 | 67.1 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 12.7 | 36.9 |
Dtbench | 85.3 | 95.5 |
Ebr Bench | 12.7 | 30.5 |
Frontiercode | 26.6 | 48.0 |
FrontierMath-Tier-4-v2-Private | 26.8 | 31.7 |
FrontierMath-Tiers-1-3-v2-Private | 66.0 | 66.0 |
Furniture Assembly | 0.0 | 14.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.4 | 92.0 |
Lmca | 65.6 | 57.0 |
Mystery Game Puzzles | 17.4 | 27.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.4 | 99.2 |
Proofbench | 50.0 | 51.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 61.1 | 71.1 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 47.0 | 49.3 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 78.0 | 67.3 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 | |
| $2.00 | $6.00 | 500K tokens (~250 books) | $30.00 |