gemini-3.7-flash
Strongest in Reliability (#22 of 188) and Abstract Reasoning (#26 of 221); weakest in Computer Use (#51 of 186). All seven dimensions are measured.
IQ profile
IQ dimensions
Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.
Benchmark results
24 of 39 Composite IQ benchmarks have a published result for gemini-3.7-flash. Benchmarks without a result stay listed so gaps are visible.
Abstract Reasoning IQ 117 · measuredBest: #12 of 76 on Chess Puzzles4/5
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23
Mathematical Reasoning IQ 128 · measuredBest: #27 of 89 on FrontierMath Tier 1-34/5
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation v1.1 · Oct 27
Full source leaderboard reconciliation · Nov 18
Academic Reasoning IQ 131 · measuredBest: #11 of 167 on SciCode5/6
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Programmatic Reasoning IQ 135 · measuredBest: #14 of 43 on IOI V22/6
Full source leaderboard reconciliation v2 · Oct 27
Full source leaderboard reconciliation · Oct 23
Computer Use IQ 121 · measuredBest: #53 of 77 on Arena.ai Agent Arena1/5
Arena.ai Agent Arena · Nov 19
Reliability IQ 126 · measuredBest: #17 of 154 on AA Long Context Reasoning v1.15/6
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Knowledge Work IQ 127 · measuredBest: #1 of 35 on AA-AnalystAgent3/6
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
Artificial Analysis v4.3.2 · Oct 20
Release & availability
Facts from the publisher's announcement and documentation.
- Released
- Developer
- Access
- Generally available through the Gemini API and Google AI Studio
- Weights
- ProprietaryHosted access only
- Inputs
- textimagevideoaudio
- Context
- 1,000,000 tokens
What Google says
- Google positions Gemini 3.7 Flash for coding, agentic workflows, and interactive applications.
- The model supports a 1M-token context window and configurable reasoning.
Publisher statements, not AI IQ measurements.
About this score
How much of gemini-3.7-flash's IQ is measured, and how the rest is estimated.
Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.
Every dimension has at least one published result. Missing benchmarks can also draw on its predecessors, Gemini 3.6 Flash and Gemini 3.5 Flash; a predecessor is an estimation input, not evidence that this model has the predecessor's measured results.
Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.
Compare gemini-3.7-flash
Side-by-side pages for the models it is most often weighed against.
Frequently asked questions
Quick answers about gemini-3.7-flash, drawn from the same data as the rest of this page.
How AI IQ scores models →Get this data from the API →- What is the IQ of gemini-3.7-flash?
- gemini-3.7-flash has an estimated IQ of 126, which ranks #28 out of 186 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
- What is gemini-3.7-flash best at?
- Among the dimensions with published benchmark results, gemini-3.7-flash ranks highest in Reliability (IQ 126, #22 of 188) and Abstract Reasoning (IQ 117, #26 of 221). Its lowest-ranked measured dimension is Computer Use (IQ 121, #51 of 186).
- What is the EQ of gemini-3.7-flash?
- gemini-3.7-flash doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for gemini-3.7-flash. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
- Which benchmarks has gemini-3.7-flash been tested on?
- gemini-3.7-flash has published results on 24 of the 39 benchmarks behind AI IQ's Composite IQ, including AA-AnalystAgent, EnterpriseOps-Gym-AA, SciCode, MMMU-Pro and AA Long Context Reasoning v1.1.
- How much does gemini-3.7-flash cost?
- AI IQ doesn't have a verified standard per-token API price for gemini-3.7-flash, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.
- Is gemini-3.7-flash open source?
- No — gemini-3.7-flash is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- Who developed gemini-3.7-flash?
- gemini-3.7-flash was developed by Google, based in the United States.
- When was gemini-3.7-flash released?
- gemini-3.7-flash was publicly released on August 13, 2026.
- How large is the context window of gemini-3.7-flash?
- gemini-3.7-flash supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
- How fast is gemini-3.7-flash?
- In independent measurements, gemini-3.7-flash generates about 284 tokens per second, with a typical response time of about 6.7 seconds.