Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
Gemini 4 Carbon vs Gemini 3.1 Pro: benchmark scores, pricing & comparison.
Side-by-side Gemini 4 Carbon vs Gemini 3.1 Pro comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Verdict: Gemini 4 Carbon ranks higher (#5 vs #47) and wins 2 of 2 shared benchmarks; Gemini 3.1 Pro costs less ($2.00/$12.0 vs $4.00/$20.0 per 1M tokens).
Rank #5 vs #47AskClash overall scores 73.8 vs 34.1.
Pricing $4.00/$20.0 vs $2.00/$12.0Input and output token prices per 1M tokens when published.
Proprietary vs ProprietaryGoogle vs Google.
Gemini 4 Carbon vs Gemini 3.1 Pro benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Gemini 4 Carbon | Gemini 3.1 Pro |
|---|---|---|
| Overall Score | 73.8 | 34.1 |
| Leaderboard Rank | #5 | #47 |
| ACB | 80.8 | — |
| Coding Agent Index | 59.4 | — |
| HLE | 60.4 | 51.4 |
| GPQA | — | 94.3 |
| SWE-bench | — | 80.6 |
| SWE-Pro | — | 54.2 |
| SWE-Atlas | 63.7 | — |
| Terminal-Bench | 65.2 | — |
| DeepSWE | — | 11.7 |
| GDPval-AA | 1732.7 | 1317.0 |
| MCP Atlas | — | 69.2 |
| Finance Agent | 67.2 | — |
| CharXiv | — | 80.2 |
| MMMU-Pro | — | 83.9 |
| ARC-AGI 2 | — | 77.1 |
| Tau2 | — | 99.3 |
| MRCR | — | 84.9 |
| Input Price (per 1M tokens) | $4.00 | $2.00 |
| Output Price (per 1M tokens) | $20.0 | $12.0 |
| Context Window | 1M | 1M |
| Benchmarks Published | 10 | 9 |
Gemini 4 Carbon vs Gemini 3.1 Pro head-to-head charts
Gemini 4 Carbon leads 3 and Gemini 3.1 Pro leads 0 of 3 shared benchmarks. Gemini 3.1 Pro is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
Gemini 4 CarbonGemini 3.1 Pro
Overall
HLE
GDPval-AA
Gemini 4 Carbon
Input$4.00
Output$20.0
Workload$8.00
Context1M
Gemini 3.1 Pro
Input$2.00
Output$12.0
Workload$4.40
Context1M
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More Gemini 4 Carbon and Gemini 3.1 Pro comparisons
Explore how Gemini 4 Carbon and Gemini 3.1 Pro stack up against other top-ranked LLMs.
Claude Fable 5.2 vs Gemini 4 CarbonClaude Fable 5.2 vs Gemini 3.1 ProClaude Opus 5.5 vs Gemini 4 CarbonClaude Opus 5.5 vs Gemini 3.1 ProClaude Sonnet 5.5 vs Gemini 4 CarbonClaude Sonnet 5.5 vs Gemini 3.1 ProClaude Fable 5.1 vs Gemini 4 CarbonClaude Fable 5.1 vs Gemini 3.1 ProGemini 4 Carbon vs Gemini 4 ArgonGemini 4 Argon vs Gemini 3.1 Pro
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.