Model Comparison
Claude Sonnet 4.6 (Non-reasoning, High Effort)
vs. Gemini 1.0 Ultra
Comparing 2 AI models · 7 benchmarks · Anthropic, Google
Recommended Pick
An Claude Sonnet 4.6 (Non-reasoning, High Effort) 4 metric wins Strongest on: Throughput, Reasoning, Intelligence
Lowest Price
Gemini 1.0 Ultra
$0.00/1M input price
Best Reasoning
Claude Sonnet 4.6 (Non-reasoning, High Effort)
45.8 reasoning score
Blends available reasoning benchmarks
Best for Coding
Claude Sonnet 4.6 (Non-reasoning, High Effort)
46.4 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Price gap
Gemini 1.0 Ultra is ∞x cheaper on input tokens than Claude Sonnet 4.6 (Non-reasoning, High Effort).
Reasoning gap
Claude Sonnet 4.6 (Non-reasoning, High Effort) leads Gemini 1.0 Ultra by 35.7 points on reasoning.
Coding gap
Claude Sonnet 4.6 (Non-reasoning, High Effort) leads Gemini 1.0 Ultra by 28.8 points on coding.
Top-pick rationale
Claude Sonnet 4.6 (Non-reasoning, High Effort) wins 4 measurable categories, including Throughput, Reasoning, Intelligence, Coding.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Claude Sonnet 4.6 (Non-reasoning, High Effort)
Anthropic
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Gemini 1.0 Ultra
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | Top Pick An Claude Sonnet 4.6 (Non-reasoning, High Effort) | Go Gemini 1.0 Ultra |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $3.00/1M | $0.00/1M |
| Output Cost | $15.00/1M | $0.00/1M |
| Blended (3:1) | $6.00/1M | — |
| Specifications | ||
| Organization | Anthropic | |
| Release Date | Feb 17, 2026 | Dec 6, 2023 |
| Performance & Speed | ||
| Throughput | 48.0 tok/s | — |
| TTFT | 1188ms | — |
| Latency | 1188ms | — |
| Composite Indices | ||
| Value Score | 100.0 | — |
| Reasoning Score | 45.8 | 10.1 |
| Intelligence | 44.4 | 10.1 |
| Coding | 46.4 | 17.6 |
| Standard Benchmarks | ||
| GPQA | 79.9% | — |
| HLE | 13.2% | — |
| SciCode | 46.9% | — |
| LCR | 57.7% | — |
| IFBench | 41.2% | — |
| TAU-bench v2 | 79.5% | — |
| TerminalBench Hard | 46.2% | — |
Key Takeaways
Gemini 1.0 Ultra offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Claude Sonnet 4.6 (Non-reasoning, High Effort) has the strongest reasoning profile with a 45.8 reasoning score, combining the available reasoning-heavy benchmarks.
Claude Sonnet 4.6 (Non-reasoning, High Effort) reaches a 46.4 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 Sonnet 4.6 (Non-reasoning, High Effort)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
Gemini 1.0 Ultra
- Cost-sensitive applications
- High-volume processing
