Claude Opus 4.8 vs JT-35B-Flash: Benchmarks, Pricing & Capabilities Compared
TL;DR — Claude Opus 4.8 wins for reasoning + long-context · JT-35B-Flash wins for general use.
Claude Opus 4.8 Anthropic
- Released
- 2026-05-28
- Context window
- 1M tokens
- Input price
- $6.25 / Mtok
- Output price
- $25.00 / Mtok
JT-35B-Flash China Mobile
- Released
- 2026-05-14
- Context window
- 256K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
Benchmark comparison
| Benchmark | Claude Opus 4.8 | JT-35B-Flash |
|---|---|---|
| AA Intelligence Index | 61.4 ✓ | 36.1 |
| GPQA Diamond | 92.0% ✓ | 82.9% |
| HLE | 45.7% ✓ | 6.1% |
| IF-Bench | 62.2% ✓ | 42.0% |
| LiveCodeBench Reasoning | 67.7% ✓ | 55.3% |
| SciCode | 53.5% ✓ | 29.1% |
| TAU2-bench | 94.4% | 99.1% ✓ |
| TerminalBench-Hard | 58.3% ✓ | 28.8% |
Pricing comparison
| Metric | Claude Opus 4.8 | JT-35B-Flash |
|---|---|---|
| Input ($/Mtok) | $6.25 | $0.00 |
| Output ($/Mtok) | $25.00 | $0.00 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $31.25 | $0.00 |
Context window & modalities
| Attribute | Claude Opus 4.8 | JT-35B-Flash |
|---|---|---|
| Context window | 1M tokens | 256K tokens |
| Input modalities | text, image | text |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ Claude Opus 4.8
Basis: GPQA Diamond
Claude Opus 4.8 92% vs JT-35B-Flash 82.9% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ Claude Opus 4.8
Basis: Context window
Claude Opus 4.8 1M tokens vs JT-35B-Flash 256K tokens.
Cost
→ JT-35B-Flash
Basis: Input $/Mtok
Claude Opus 4.8 $6.25/Mtok vs JT-35B-Flash $0/Mtok input.
Changelog & releases
Claude Opus 4.8
Released 2026-05-28
JT-35B-Flash
Released 2026-05-14