Ling-2.6-flash ling-2.6-flash
inclusionai · ling
#71 overall
- params
- 107.5B
- arch
- moe
- license
- mit open weights
# architecture
- layers
- 32
- d_model
- 4096
- heads
- 32q / 32kv
- head dim
- 128
- experts
- top-8 of 256 + 1 shared
- vocab
- 157184
- family
- bailing_hybrid
signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.
# why ranked
Overall: #71 — score 34.0 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | 31.3 |
| bench_composite | 0.30 | 40.3 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aa-coding-v1 | 40.3 |
Coding: provisional — score 30.1 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.30 | 30.1 |
| aider_polyglot | 0.30 | — |
| swe_bench_verified | 0.40 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 25.3 | Artificial Analysis | — |
| AA Intelligence Index | 9.7 | Artificial Analysis | — |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M cache | price src | tps | uptime | ✓ |
|---|---|---|---|---|---|---|---|---|---|
| Novita | 256k | $0.10 | $0.30 | — | via requesty | — | — |
sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price
source aliases
- openrouter
inclusionai/ling-2.6-flash