| Benchmark | Score | Δ vs prior | Rank (current) | Configuration | Source |
|---|---|---|---|---|---|
τ²-bench (Telecom) | 14.9% | #10 of 10 | leaderboard | benchlm.ai ↗ | |
Artificial Analysis Intelligence Index | 14.1 | #11 of 11 | leaderboard | benchlm.ai ↗ |
| Version | Released | $ in / out | Terminal-Bench | SWE-bench | GPQA | HLE | ARC-AGI-2 | τ²-bench |
|---|---|---|---|---|---|---|---|---|
| Gemini 2.5 Pro | $1.25 / $10 | — | 63.8% | — | 18.8% | — | 54.1% | |
| Gemini 2.5 Flash | $0.3 / $2.5 | — | — | — | — | — | 14.9% | |
| Gemini 3 Pro | $2 / $12 | — | 76.2% | 91.9% | 37.5% | 31.1% | 87.1% | |
| Gemini 3 Flash | $0.5 / $3 | 53.9% | 78% | 90.4% | 33.7% | — | 43.3% | |
| Gemini 3.1 Pro | $2 / $12 | 70.8% | — | 94.3% | 44.4% | 77.1% | 95.6% | |
| Gemini 3.5 Flash | $1.5 / $9 | 74.2% | — | 92.7% | 40.2% | 72.1% | 95.3% | |
| Gemini 3.6 Flash | $0.75 / $3.75 | 73.8% | — | — | — | 60.4% | — | |
| Gemini 3.7 Flash | $0.75 / $3.75 | 77.5% | — | — | — | 84.6% | — | |
| Gemini 3.8 Flash | $0.75 / $3.75 | 81.3% | — | — | — | 89.2% | — | |
| Gemini 4 Argon | $2 / $10 | — | — | — | — | — | — |