Claude Opus 4.6 Benchmark Details
Claude Opus 4.6 currently shows benchmark results led by IF Bench (1 / 282, score 94), τ²-Bench - Telecom (2 / 264, score 99.25), HumanEval (2 / 140, score 95). This page also compares it with 2 competitor models and 3 predecessor or same-series models, including performance and pricing views when available. 6 source links are attached for reference.
Benchmark Results
Benchmark Results
Knowledge Exams
6 evaluationsCode Generation & Editing
3 evaluationsAbstract Generalization
11 evaluationsScientific Reasoning
6 evaluationsHonesty & Factuality
3 evaluationsRepository Engineering
4 evaluationsMathematics
12 evaluationsVisual Understanding
6 evaluationsService Workflows
6 evaluationsInstruction Following
3 evaluationsAgentic Development
3 evaluationsMemory & Persistence
5 evaluationsTool Orchestration
4 evaluationsML Engineering
2 evaluationsClinical Workflows
4 evaluationsCompetitor Comparison
Benchmark scores for Claude Opus 4.6 compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Opus 4.6Current | GPT-5.4 | Gemini 3.1 Pro Preview |
|---|---|---|---|
53.00Extended Thinking ｜ Tools | 52.10Thinking Level · Extra High ｜ Tools | 51.40Thinking Level · High ｜ Tools | |
91.05Extended Thinking | -- | 92.60Thinking Level · High | |
57.57Standard Mode ｜ Tools | 48.47Thinking Level · Extra High ｜ Tools | 32.03Thinking Level · High ｜ Tools | |
94.00Thinking Level · High | 93.67Thinking Level · Extra High | -- | |
69.17Thinking Level · High | 77.10Standard Mode | 77.10Thinking Level · High | |
ARC-AGI-3 (Standard harness) Action efficiency score（以 ARC Prize Standard harness 口径为准） Abstract Generalization | 0.51Thinking Level · High | 0.21Thinking Level · High | 0.42Thinking Level · High |
12.60Thinking Level · High | 23.40Thinking Level · Extra High | 17.70Thinking Enabled | |
91.31Extended Thinking | 92.00Thinking Level · Extra High | 94.30Thinking Level · High | |
13.67Thinking Enabled | 5.78Thinking Level · High | -- | |
47.10Thinking Enabled ｜ Tools | 43.40Thinking Level · Extra High ｜ Tools | 32.20Thinking Enabled ｜ Tools | |
80.84Extended Thinking ｜ Tools | -- | 80.60Thinking Level · High ｜ Tools | |
96.67Thinking Level · High ｜ Tools | 99.17Thinking Level · Extra High ｜ Tools | -- |
Standard API Pricing: Claude Opus 4.6 vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
When a context threshold exists, the charted base price only applies within these limits:
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Claude Opus 4.6 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
GPT-5.4 | OpenAI | $2.5 / 1M tokens | $15 / 1M tokens | — |
Gemini 3.1 Pro Preview | Google DeepMind | $2 / 1M tokens | $12 / 1M tokens | <= 200K |
Version History
How each version of the Claude Opus 4.6 series stacks up on benchmark tests
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | Claude Opus 4.6Current | Opus 4.5 | Opus 4.1 | Claude Opus 4 |
|---|---|---|---|---|
53.00Extended Thinking ｜ Tools | 43.20Extended Thinking ｜ Tools | 12.50Thinking Enabled | 12.30Thinking Enabled | |
57.57Standard Mode ｜ Tools | 20.63Thinking Level · High ｜ Tools | -- | -- | |
94.00Thinking Level · High | 80.00Extended Thinking | -- | 35.67Standard Mode | |
69.17Thinking Level · High | 37.64Extended Thinking | -- | 8.61Standard Mode | |
12.60Thinking Level · High | 4.60Thinking Enabled | -- | -- | |
91.31Extended Thinking | 87.00Extended Thinking | 81.00Extended Thinking | 79.60Standard Mode | |
13.67Thinking Enabled | 14.00Thinking Enabled | -- | -- | |
80.84Extended Thinking ｜ Tools | 80.90Extended Thinking ｜ Tools | 74.50Extended Thinking ｜ Tools | 72.50Standard Mode | |
96.67Thinking Level · High ｜ Tools | 93.30Extended Thinking | -- | -- | |
99.79Extended Thinking | 91.30Thinking Enabled | 80.30Thinking Enabled | 75.50Standard Mode | |
40.70Thinking Level · High | 20.70Extended Thinking | 7.20Extended Thinking | 4.50Standard Mode | |
22.90Thinking Level · High | 4.20Standard Mode | 4.2032K | 4.2032K |
Single-Benchmark Version Trend
Viewing: HLE · Knowledge Exams
Standard API Pricing Across the Claude Opus 4.6 Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Claude Opus 4.6 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
Opus 4.5 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
Opus 4.1 | Anthropic | $15 / 1M tokens | $75 / 1M tokens | — |
Claude Opus 4 | Anthropic | $15 / 1M tokens | $75 / 1M tokens | — |