Compare · ModelsLive · 2 picked · head to head
Claude Opus 4.8 vs Claude Opus 5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Opus 5 wins on 21/21 benchmarks
Claude Opus 5 wins 21 of 21 shared benchmarks. Leads in agentic · reasoning · knowledge.
Category leads
agentic·Claude Opus 5reasoning·Claude Opus 5knowledge·Claude Opus 5coding·Claude Opus 5general·Claude Opus 5math·Claude Opus 5
Hype vs Reality
Attention vs performance
Claude Opus 4.8
#75 by perf·#9 by attention
Claude Opus 5
#21 by perf·#9 by attention
Best value
Claude Opus 5
1.3x better value than Claude Opus 4.8
Claude Opus 4.8
3.7 pts/$
$15.00/M
Claude Opus 5
4.6 pts/$
$15.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Anthropic
$965.0B·Tier 1
Head to head
21 benchmarks · 2 models
Claude Opus 4.8Claude Opus 5
APEX-Agents
Claude Opus 5 leads by +16.9
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Opus 4.8
48.9
Claude Opus 5
65.8
ARC-AGI
Claude Opus 5 leads by +5.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Opus 4.8
92.5
Claude Opus 5
97.5
ARC-AGI-2
Claude Opus 5 leads by +18.3
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 4.8
72.1
Claude Opus 5
90.4
Chess Puzzles
Claude Opus 5 leads by +8.4
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Opus 4.8
30.6
Claude Opus 5
39.0
Deepswe
Claude Opus 5 leads by +14.7
Claude Opus 4.8
59.0
Claude Opus 5
73.7
Dtbench
Claude Opus 5 leads by +4.9
Claude Opus 4.8
91.5
Claude Opus 5
96.5
Ebr Bench
Claude Opus 5 leads by +17.1
Claude Opus 4.8
28.6
Claude Opus 5
45.7
Frontiercode
Claude Opus 5 leads by +6.9
Claude Opus 4.8
46.5
Claude Opus 5
53.4
FrontierMath-Tier-4-v2-Private
Claude Opus 5 leads by +17.1
Claude Opus 4.8
56.1
Claude Opus 5
73.2
FrontierMath-Tiers-1-3-v2-Private
Claude Opus 5 leads by +5.6
Claude Opus 4.8
80.0
Claude Opus 5
85.6
Furniture Assembly
Claude Opus 5 leads by +26.2
Claude Opus 4.8
17.9
Claude Opus 5
44.0
GPQA diamond
Claude Opus 5 leads by +3.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 4.8
88.0
Claude Opus 5
91.8
Lmca
Claude Opus 5 leads by +8.2
Claude Opus 4.8
67.7
Claude Opus 5
75.8
Mystery Game Puzzles
Claude Opus 5 leads by +25.3
Claude Opus 4.8
29.5
Claude Opus 5
54.8
Osworld 2 0
Claude Opus 5 leads by +10.8
Claude Opus 4.8
20.6
Claude Opus 5
31.4
OTIS Mock AIME 2024-2025
Claude Opus 5 leads by +0.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 4.8
98.3
Claude Opus 5
98.9
PostTrainBench
Claude Opus 5 leads by +1.2
Claude Opus 4.8
33.8
Claude Opus 5
35.0
Proofbench
Claude Opus 5 leads by +30.0
Claude Opus 4.8
69.0
Claude Opus 5
99.0
SimpleBench
Claude Opus 5 leads by +19.0
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Opus 4.8
57.8
Claude Opus 5
76.7
SimpleQA Verified
Claude Opus 5 leads by +6.9
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Opus 4.8
53.0
Claude Opus 5
59.9
WeirdML
Claude Opus 5 leads by +8.9
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Opus 4.8
82.9
Claude Opus 5
91.8
Full benchmark table
| Benchmark | Claude Opus 4.8 | Claude Opus 5 |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 48.9 | 65.8 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 92.5 | 97.5 |
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. | 72.1 | 90.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 30.6 | 39.0 |
Deepswe | 59.0 | 73.7 |
Dtbench | 91.5 | 96.5 |
Ebr Bench | 28.6 | 45.7 |
Frontiercode | 46.5 | 53.4 |
FrontierMath-Tier-4-v2-Private | 56.1 | 73.2 |
FrontierMath-Tiers-1-3-v2-Private | 80.0 | 85.6 |
Furniture Assembly | 17.9 | 44.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 88.0 | 91.8 |
Lmca | 67.7 | 75.8 |
Mystery Game Puzzles | 29.5 | 54.8 |
Osworld 2 0 | 20.6 | 31.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.3 | 98.9 |
PostTrainBench | 33.8 | 35.0 |
Proofbench | 69.0 | 99.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 57.8 | 76.7 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 53.0 | 59.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 82.9 | 91.8 |
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 | |
| $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 |