token.app › Compare › Inkling vs Gemini 3.7 Flash
Inkling vs Gemini 3.7 Flash
Gemini 3.7 Flash leads on 4 of 4 shared benchmarks. Gemini 3.7 Flash is 1.2× cheaper per token on a blended 3:1 basis. Gemini 3.7 Flash accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Inkling | Gemini 3.7 Flash | |
|---|---|---|
| Provider | Thinkingmachines | |
| Input $/1M | $1.00 | $0.750 |
| Output $/1M | $4.05 | $3.75 |
| Blended $/1M | $1.76 | $1.50 |
| Context window | 524K | 1.0M |
| Max output | 472K | 66K |
| Released | Jul 2026 | Aug 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 88.3% | 94.8% |
| FrontierMath T1–3 | 33.3% | 71.6% |
| FrontierMath T4 | 4.9% | 36.6% |
| OTIS Mock AIME | 88.9% | 97.2% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Inkling if…
- Open weights — self-hostable
Choose Gemini 3.7 Flash if…
- Costs less per token — $1.50 vs $1.76 blended
- Higher GPQA Diamond (94.8% vs 88.3%)
- Higher FrontierMath T1–3 (71.6% vs 33.3%)
- Higher FrontierMath T4 (36.6% vs 4.9%)
- Higher OTIS Mock AIME (97.2% vs 88.9%)
- Larger context window (1.0M)
- Newer model (released Aug 2026)
FAQ
Which is better, Inkling or Gemini 3.7 Flash?
Across the 4 benchmarks both models have independently-run scores for, Inkling leads on 0 and Gemini 3.7 Flash leads on 4. Benchmarks are one input — price and context window are on this page too.
Is Inkling cheaper than Gemini 3.7 Flash?
Gemini 3.7 Flash is cheaper: $1.50 versus $1.76 per million tokens blended at 3:1 input:output. Input alone: $1.00 vs $0.750. Output alone: $4.05 vs $3.75.
What context windows do Inkling and Gemini 3.7 Flash have?
Inkling: 524,288 tokens. Gemini 3.7 Flash: 1,048,576 tokens.
Who makes Inkling and Gemini 3.7 Flash?
Inkling is made by Thinkingmachines. Gemini 3.7 Flash is made by Google.