Claude 3 Opus (2024-02-29) vs Gemini 3.1 Pro preview
Claude 3 Opus (2024-02-29) vs Gemini 3.1 Pro preview: Gemini 3.1 Pro preview is cheaper by 87% on average. Claude 3 Opus (2024-02-29) from Anthropic (200,000-token context, tool calls) vs. Gemini 3.1 Pro preview from Google Vertex AI (1,048,576-token context, reasoning, tool calls). Use Agent Command Center to A/B both in shadow mode and pick the winner per workload.
Side-by-side cost
Live workload comparison
Same workload run through both models. The cheaper one is highlighted.
3,000
01,048,576
400
065,536
5,000
01,000,000
At this workload, Gemini 3.1 Pro preview is 86% cheaper than Claude 3 Opus (2024-02-29) — a savings of $9,770/month ($117,245/year).
Production recipe — Agent Command Center
strategy: cost-optimized
primary:
model: gemini-3-1-pro-preview
provider: vertex-ai
fallback:
model: claude-3-opus-20240229
provider: anthropic
shadow: { sample_rate: 0.05 } # mirror 5% of traffic to compare quality live| Claude 3 Opus (2024-02-29) | Gemini 3.1 Pro preview | |
|---|---|---|
| Input price | $15.00/M | $2.00/M |
| Output price | $75.00/M | $12.00/M |
| Context window | 200,000 | 1,048,576 |
| Max output | 4,096 | 65,536 |
| Function calling | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio input | — | ✓ |
| Reasoning | — | ✓ |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Pricing verified | May 12, 2026 | May 12, 2026 |
Benchmark comparison
Side-by-side public benchmark scores. Greener bar = winner.
Chatbot Arena ELOgeneral
Claude 3 Opus (2024-02-29)
1,248
Gemini 3.1 Pro preview
1,492
GPQA Diamondreasoning
Claude 3 Opus (2024-02-29)
—
Gemini 3.1 Pro preview
94.3%
SWE-bench Verifiedagent
Claude 3 Opus (2024-02-29)
—
Gemini 3.1 Pro preview
80.6%
ARC-AGI-2reasoning
Claude 3 Opus (2024-02-29)
—
Gemini 3.1 Pro preview
77.1%
Humanity's Last Examreasoning
Claude 3 Opus (2024-02-29)
—
Gemini 3.1 Pro preview
44.4%