Gemini 3.5 Flash vs JT-35B-Flash: Benchmarks, Pricing & Capabilities Compared
TL;DR — Gemini 3.5 Flash wins for long-context · JT-35B-Flash wins for general use.
Gemini 3.5 Flash Google
- Released
- 2026-05-19
- Context window
- 1M tokens
- Input price
- $1.50 / Mtok
- Output price
- $9.00 / Mtok
JT-35B-Flash China Mobile
- Released
- 2026-05-14
- Context window
- 256K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
Benchmark comparison
| Benchmark | Gemini 3.5 Flash | JT-35B-Flash |
|---|---|---|
| AA Intelligence Index | 43.3 ✓ | 36.1 |
| GPQA Diamond | 82.8% | 82.9% ✓ |
| HLE | 23.1% ✓ | 6.1% |
| IF-Bench | 47.3% ✓ | 42.0% |
| LiveCodeBench Reasoning | 53.3% | 55.3% ✓ |
| SciCode | 48.8% ✓ | 29.1% |
| TAU2-bench | 58.8% | 99.1% ✓ |
| TerminalBench-Hard | 46.2% ✓ | 28.8% |
Pricing comparison
| Metric | Gemini 3.5 Flash | JT-35B-Flash |
|---|---|---|
| Input ($/Mtok) | $1.50 | $0.00 |
| Output ($/Mtok) | $9.00 | $0.00 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $10.50 | $0.00 |
Context window & modalities
| Attribute | Gemini 3.5 Flash | JT-35B-Flash |
|---|---|---|
| Context window | 1M tokens | 256K tokens |
| Input modalities | text, image, audio, video | text |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ JT-35B-Flash
Basis: GPQA Diamond
Gemini 3.5 Flash 82.8% vs JT-35B-Flash 82.9% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ Gemini 3.5 Flash
Basis: Context window
Gemini 3.5 Flash 1M tokens vs JT-35B-Flash 256K tokens.
Cost
→ JT-35B-Flash
Basis: Input $/Mtok
Gemini 3.5 Flash $1.5/Mtok vs JT-35B-Flash $0/Mtok input.
Changelog & releases
Gemini 3.5 Flash
Released 2026-05-19
JT-35B-Flash
Released 2026-05-14