OLMo 2 32B Instruct (0325) in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
C 1,217 ±7
Percentile 25 · #223 · provisional
People prefer / Solves tasks
1,218 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
C General 1,217 [1,210–1,224] Percentile 25 · #223 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,218 ±5.50 | 1,218 ±6 | 35.6% | 2026-11-11 | 0325 |
| LMArena |
text/hard_prompts
|
1,208 ±10 | 1,221 ±9 | 29.6% | 2026-11-11 | 0325 |
| LMArena |
text/instruction_following
|
1,186 ±8.79 | 1,210 ±8 | 15.4% | 2026-11-11 | 0325 |
| LMArena |
text/multi_turn
|
1,221 ±15 | 1,237 ±14 | 5.6% | 2026-11-11 | 0325 |
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 [1,190–1,230] Percentile 22 · #224 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,210 ±14 | 1,212 ±12 | 82.6% | 2026-11-11 | 0325 |
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 1,208 [1,186–1,230] Percentile 24 · #194 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,208 ±14 | 1,208 ±14 | 81.2% | 2026-11-11 | 0325 |
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 1,220 [1,198–1,243] Percentile 26 · #197 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,198 ±13 | 1,222 ±13 | 90.2% | 2026-11-11 | 0325 |
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 1,233 [1,220–1,246] Percentile 29 · #192 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,255 ±6.62 | 1,235 ±7 | 92.9% | 2026-11-11 | 0325 |
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 1,214 [1,188–1,240] Percentile 14 · #199 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,187 ±17 | 1,215 ±15 | 88.9% | 2026-11-11 | 0325 |
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 | 2026-11 |
|---|---|
| OLMo 2 32B Instruct (0325) | 1,217 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.