Model Comparison
Claude 3.5 Sonnet (June '24)
vs. Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Comparing 2 AI models · 10 benchmarks · Anthropic
Recommended Pick
An Claude Opus 4.6 (Adaptive Reasoning, Max Effort) 8 metric wins Strongest on: Value, Throughput, Reasoning
Best Value
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
100.0 value score
59.7 reasoning / $10.00/1M
Lowest Price
Claude 3.5 Sonnet (June '24)
$3.00/1M input price
Best Reasoning
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
59.7 reasoning score
Blends available reasoning benchmarks
Best for Coding
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
48.1 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
Claude 3.5 Sonnet (June '24) is 1.7x cheaper on input tokens than Claude Opus 4.6 (Adaptive Reasoning, Max Effort).
Reasoning gap
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) leads Claude 3.5 Sonnet (June '24) by 29.1 points on reasoning.
Coding gap
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) leads Claude 3.5 Sonnet (June '24) by 22.1 points on coding.
Top-pick rationale
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) wins 8 measurable categories, including Value, Throughput, Reasoning, Intelligence.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Claude 3.5 Sonnet (June '24)
Anthropic
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Anthropic
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | An Claude 3.5 Sonnet (June '24) | Top Pick An Claude Opus 4.6 (Adaptive Reasoning, Max Effort) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $3.00/1M | $5.00/1M |
| Output Cost | $15.00/1M | $25.00/1M |
| Blended (3:1) | $6.00/1M | $10.00/1M |
| Specifications | ||
| Organization | Anthropic | Anthropic |
| Release Date | Jun 21, 2024 | Feb 5, 2026 |
| Performance & Speed | ||
| Throughput | — | 49.6 tok/s |
| TTFT | — | 12090ms |
| Latency | — | 12090ms |
| Composite Indices | ||
| Value Score | 85.4 | 100.0 |
| Reasoning Score | 30.6 | 59.7 |
| Intelligence | 14.2 | 52.9 |
| Coding | 26.0 | 48.1 |
| Standard Benchmarks | ||
| GPQA | 56.0% | 89.6% |
| MMLU Pro | 75.1% | — |
| HLE | 3.7% | 36.7% |
| MATH 500 | 69.5% | — |
| AIME (Original) | 9.7% | — |
| SciCode | 31.6% | 51.9% |
| LCR | — | 70.7% |
| IFBench | — | 53.1% |
| TAU-bench v2 | — | 92.1% |
| TerminalBench Hard | — | 46.2% |
Key Takeaways
Claude 3.5 Sonnet (June '24) offers the best value at $3.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) has the strongest reasoning profile with a 59.7 reasoning score, combining the available reasoning-heavy benchmarks.
Claude Opus 4.6 (Adaptive Reasoning, Max Effort) reaches a 48.1 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Claude 3.5 Sonnet (June '24)
- Cost-sensitive applications
- High-volume processing
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
