internlm2_5-20b-chat in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,173 ±4
Percentile 20 · #233 · provisional
People prefer / Solves tasks
1,171 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,173 [1,169–1,177] Percentile 20 · #233 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,158 ±3.60 | 1,158 ±4 | 27.0% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,158 ±5.78 | 1,176 ±5 | 25.5% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,135 ±5.08 | 1,162 ±5 | 13.0% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,150 ±11 | 1,190 ±9 | 10.4% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,135 ±7.43 | 1,159 ±7 | 5.9% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,149 ±8.30 | 1,166 ±8 | 5.6% | 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
D Coding 1,170 [1,159–1,182] Percentile 18 · #228 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,159 ±7.17 | 1,166 ±6 | 89.0% | 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 Math 1,185 [1,172–1,197] Percentile 22 · #200 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,180 ±7.53 | 1,182 ±7 | 86.6% | 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
D Writing 1,156 [1,145–1,167] Percentile 19 · #217 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,123 ±8.10 | 1,145 ±8 | 61.1% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,149 ±8.30 | 1,166 ±8 | 31.4% | 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: 繁體中文 1,214 [1,200–1,227] Percentile 17 · #185 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,199 ±9.54 | 1,214 ±8 | 92.7% | 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: English 1,181 [1,172–1,190] Percentile 23 · #210 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,203 ±4.71 | 1,180 ±5 | 93.5% | 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 1,148 [1,135–1,161] Percentile 10 · #210 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,107 ±8.01 | 1,143 ±7 | 92.9% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| internlm2_5-20b-chat | 1,173 D |
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.