trinity-large-preview in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,331 ±2
Percentile 42 · #169 · provisional
People prefer / Solves tasks
1,339 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,331 [1,329–1,333] Percentile 42 · #169 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,339 ±2.17 | 1,339 ±2 | 25.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,350 ±2.67 | 1,349 ±2 | 25.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,334 ±3.41 | 1,350 ±3 | 12.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,351 ±5.95 | 1,354 ±5 | 11.9% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,355 ±3.28 | 1,358 ±3 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,342 ±4.39 | 1,346 ±4 | 6.2% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
C Coding 1,349 [1,343–1,354] Percentile 44 · #157 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,381 ±3.72 | 1,364 ±3 | 90.1% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
C Math 1,315 [1,303–1,326] Percentile 36 · #163 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,336 ±7.01 | 1,332 ±7 | 86.9% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
C Writing 1,342 [1,336–1,348] Percentile 47 · #142 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,321 ±4.66 | 1,347 ±5 | 61.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,355 ±3.28 | 1,358 ±3 | 32.4% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
C Language: 繁體中文 1,328 [1,318–1,338] Percentile 33 · #150 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,353 ±7.03 | 1,337 ±6 | 93.4% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
C Language: Deutsch 1,316 [1,293–1,338] Percentile 26 · #107 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,313 ±15 | 1,328 ±13 | 90.4% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
C Language: English 1,335 [1,329–1,341] Percentile 42 · #160 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,358 ±2.96 | 1,344 ±3 | 93.9% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Language: Español 1,346 [1,330–1,362] Percentile 21 · #118 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,356 ±9.83 | 1,358 ±9 | 92.1% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Language: Français 1,350 [1,332–1,367] Percentile 23 · #104 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,374 ±11 | 1,363 ±10 | 91.8% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Language: 한국어 1,317 [1,297–1,337] Percentile 20 · #109 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,259 ±15 | 1,328 ±11 | 91.1% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
D Language: Polski 1,305 [1,286–1,325] Percentile 5 · #125 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,291 ±13 | 1,315 ±11 | 91.2% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
C Language: Русский 1,330 [1,322–1,339] Percentile 35 · #153 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,324 ±5.18 | 1,339 ±5 | 93.6% | 2026-10-02 | — |
Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology
History
The same in a table
| Model | 2026-10 |
|---|---|
| trinity-large-preview | 1,331 C |
Badge
Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.
Data CC BY 4.0: keep the link to fedi.software.