Benchmark avg
38.5
7 tracked scores
Google · Proprietarygemini-2.0-flash-thinking-exp-01-21
Active
Model portfolio
gemini-2.0-flash-thinking-exp-01-21
Tap a star to rate
Google · Released 2024-12-11 · v2024-12-11 · Closed · Context 1M tokens
Language Cap
136
Cadle Language Cap 136 · 79%
Benchmark average
—
Not enough benchmark results yet
Pricing
$0.10
$0.40 / 1M out
CADLE INSIGHTS
Only measured signals
Strongest signal
lech-mazur-writing
Score 73.8
Blended $/1M
$0.50
In $0.10 · Out $0.40
Value index
77.1
Quality ÷ blended $/1M (higher is better)
Context
1M
Provider context window (not max output)
SPEED · COST · QUALITY
Measured matrix and verified gateway observations only.
- Input $/1M
- $0.10
- Output $/1M
- $0.40
DESCRIPTION + DETAILS
PROVIDER
RELEASE
2024-12-11
CONTEXT
1M tokens
STATUS
ACTIVE
COMMUNITY REVIEWS
Community Reviews & Field Notes
Verified EngineersReal operator evaluations, prompt robustness observations, and deployment notes for gemini-2.0-flash-thinking-exp-01-21.
4.5(2)
Leave a Field Observation
Rating:5 - Frontier benchmark
Role:
Tag topic:
Reviews are publicly visible to the engineering community.
Inference OperatorProduction Deployer Verified
Oct 28, 2026
Tested gemini-2.0-flash-thinking-exp-01-21 on high-concurrency tool loops. Token generation remains consistent under sustained context load, with minimal prompt drift on complex JSON schemas.
Autonomous Agent LeadEval Maintainer Verified
Oct 24, 2026
Evaluated gemini-2.0-flash-thinking-exp-01-21 on multi-turn code synthesis. Code reasoning and diff application succeed on ~88% of test suites. Best paired with strict system prompt guardrails.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | |
| Release | 2024-12-11 |
| Input / 1M | $0.10 |
| Output / 1M | $0.40 |
| Context | 1M tokens |
| Cadle Cap | 136 |
| Cap board | Cadle Language Cap 136 |
| aider-polyglot | 5.8 |
| fiction-livebench | 52.8 |
| lech-mazur-writing | 73.8 |
| simplebench | 16.8 |
| otis-mock-aime-2024-2025 | 57.7 |
| gpqa-diamond | 44.5 |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations
SOURCE TRACKING
Evidence linked to this model — listing, hub, benchmarks, or live gateway prices.
API
Google listing