Back to models
Intelligence Index
High setting
39.1
Measured · Artificial Analysis v4.3.2- Maximum input
- 1.05M tok
Performance profile
ReasoningArchived source
94.5%
GPQA DiamondCodingArchived source
57.2%
SciCodeCost efficiencyArchived source
42.2pts / $
Intelligence ÷ eval costCapabilities
Maximum input
Modalities
Reasoning modes
Integration
Reasoning trade-offs
Source (opens in a new tab)Gemini 3.7 Flash
Cost per task (USD)
Gemini 3.7 FlashHigh
- Intelligence Index
- 39.1
- Cost / task
- $0.9253
- Evaluation time
- 3.2m
Pricing & access
USD per 1M tokens
- Input
- $0.75
- Output
- $3.75
- Cached input
- $0.075
Gemini API tool compatibility (opens in a new tab)
- Code execution
- Computer use (preview)
- File search
- Maps
- Web search
- URL context
Benchmarks
Full leaderboardSource (opens in a new tab)47.9%57.2%13.6%81.7%1,371 Elo
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 4Claude Sonnet 5.5Max55.0%
- 5GPT-6 AstraMax54.7%
- 6Muse Wonder FullMax53.6%
- 7GPT-6.1 SolMax52.9%
- 8Muse WonderMax50.1%
- 9MiMo-V2.6-ProReasoning49.4%
- 10Muse Spark 1.3Max48.7%
Peers use their best measured result on this benchmark.
Inspect conflicting source claims
Some sources disagree. The selected claim follows the catalog’s source precedence.
Gemini 3.7 Flash
Selected claim · release-dates-ai-google-dev
Original source (opens in a new tab){
"context_window": null,
"family": null,
"input_modalities": [
"text",
"image",
"video",
"audio"
],
"license": null,
"lifecycle": "active",
"max_output_tokens": 65536,
"name": "Gemini 3.7 Flash",
"output_modalities": [
"text"
],
"release_date": "2026-08-13",
"weights": "closed"
}Alternate claim · google-docs
Original source (opens in a new tab){
"context_window": null,
"family": null,
"input_modalities": [
"text",
"image",
"video",
"audio"
],
"license": null,
"lifecycle": "deprecated",
"max_output_tokens": 65536,
"name": "Gemini 3.7 Flash",
"output_modalities": [
"text"
],
"release_date": null,
"weights": "closed"
}Alternate claim · livebench
Original source (opens in a new tab){
"context_window": null,
"family": null,
"input_modalities": null,
"license": null,
"lifecycle": "unknown",
"max_output_tokens": null,
"name": "Gemini 3.7 Flash",
"output_modalities": null,
"release_date": null,
"weights": "unknown"
}