Claude Opus 4.8 vs Gemini 3.1 Pro Preview
Side-by-side comparison across metrics, pricing, and overall score — every value traced to a source.
Verdict: Claude Opus 4.8 ranks highest overall (#2) with a score of 56.0.
The best choice still depends on which metrics matter for your workload — per-metric winners are marked below.
What the numbers hide
Computed from the published values below — no estimates, no generated claims.
Fragile verdict
The overall winner flips to Claude Opus 4.8 if SWE-Bench Pro Score is weighted at 50% (it counts for 29% today). If swe-bench pro score drives your decision, the ranking above may not be your ranking.
Fragile verdict
The overall winner flips to Claude Opus 4.8 if Max Output Tokens is weighted at 30% (it counts for 6% today). If max output tokens drives your decision, the ranking above may not be your ranking.
Real tradeoff
Claude Opus 4.8 clearly beats Gemini 3.1 Pro Preview on Max Output Tokens but clearly loses on Input Price — this pair is a priorities question, not a quality question.
AI hot take
Sign in to generate a contrarian AI read of this comparison.
| Metric | Claude Opus 4.8Anthropic | Gemini 3.1 Pro PreviewGoogle |
|---|---|---|
| Overall OptiSift Score | 56.0#2 | 50.8#5 |
| Input Price | $5 | $2 |
| Output Price | $25 | $12 |
| Cache Read Price | $0.5 | $0.2 |
| Context Window | 1M | 1.0M |
| Max Output Tokens | 128K | 66K |
| SWE-Bench Pro Score | 69.2% | 54.2% |
| Tool Calling | Yes | Yes |
| Extended Reasoning | Yes | Yes |
About these models
#2Claude Opus 4.8
Anthropic
Claude Opus 4.8 is Anthropic's reasoning-capable model: $5/$25 per 1M input/output tokens, 1M token context window, 69.2% on SWE-Bench Pro.
#5Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is Google's reasoning-capable model: $2/$12 per 1M input/output tokens, 1.0M token context window, 54.2% on SWE-Bench Pro.