nemotron-4-340b-instruct in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,219 ±3
Percentile 25 · #219 · provisional
People prefer / Solves tasks
1,220 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,219 [1,216–1,222] Percentile 25 · #219 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,225 ±2.69 | 1,225 ±3 | 26.7% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,202 ±4.53 | 1,216 ±4 | 25.6% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,203 ±4.14 | 1,227 ±4 | 12.9% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,171 ±9.56 | 1,207 ±8 | 10.8% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,214 ±5.85 | 1,230 ±5 | 6.1% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,225 ±6.79 | 1,237 ±6 | 5.8% | 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 Coding 1,210 [1,201–1,219] Percentile 22 · #216 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,209 ±5.74 | 1,211 ±5 | 89.6% | 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
C Math 1,215 [1,205–1,225] Percentile 25 · #191 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,216 ±6.12 | 1,217 ±6 | 87.4% | 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 Writing 1,228 [1,220–1,236] Percentile 27 · #197 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,203 ±5.92 | 1,227 ±6 | 62.4% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,225 ±6.79 | 1,237 ±6 | 30.8% | 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: 繁體中文 1,224 [1,214–1,234] Percentile 20 · #179 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,214 ±6.77 | 1,226 ±5 | 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
D Language: Deutsch 1,221 [1,203–1,239] Percentile 16 · #121 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,192 ±12 | 1,223 ±10 | 91.6% | 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
C Language: English 1,214 [1,207–1,222] Percentile 26 · #201 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,236 ±3.67 | 1,215 ±4 | 93.8% | 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: Español 1,208 [1,182–1,234] Percentile 8 · #137 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,195 ±16 | 1,209 ±15 | 88.9% | 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: Français 1,200 [1,172–1,227] Percentile 10 · #122 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,195 ±17 | 1,199 ±16 | 88.2% | 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
D Language: 日本語 1,222 [1,202–1,242] Percentile 11 · #114 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,128 ±15 | 1,223 ±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: 한국어 1,240 [1,221–1,259] Percentile 13 · #119 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,147 ±14 | 1,243 ±10 | 91.5% | 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: Русский 1,242 [1,231–1,252] Percentile 19 · #189 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,219 ±6.43 | 1,244 ±6 | 93.3% | 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 |
|---|---|
| nemotron-4-340b-instruct | 1,219 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.