MiMo-V2-Omni in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,406 ±3
Percentile 71 · #85 · provisional
People prefer / Solves tasks
1,419 / —
Human votes vs benchmarks, Elo-eq
Value
+46
$0.4875 per 1M tokens, median of 2 providers · vendor $0.175
On your hardware
Closed weights: cloud only.
Score decomposition
B General 1,406 [1,403–1,409] Percentile 71 · #85 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,423 ±2.82 | 1,423 ±3 | 25.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,445 ±3.38 | 1,435 ±3 | 25.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,428 ±4.08 | 1,440 ±4 | 12.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,449 ±6.65 | 1,435 ±5 | 11.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,442 ±3.87 | 1,440 ±4 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,445 ±5.46 | 1,440 ±5 | 6.0% | 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
B Coding 1,417 [1,410–1,424] Percentile 76 · #69 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,467 ±4.38 | 1,441 ±4 | 90.0% | 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
B Math 1,390 [1,374–1,406] Percentile 63 · #95 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,431 ±9.76 | 1,423 ±9 | 85.2% | 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 Vision 1,399 [1,394–1,404] Percentile 46 · #62 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,228 ±3.75 | 1,410 ±3 | 63.4% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,238 ±4.04 | 1,412 ±4 | 15.6% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,256 ±6.16 | 1,424 ±6 | 14.7% | 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
B Writing 1,413 [1,406–1,420] Percentile 70 · #80 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,392 ±5.49 | 1,421 ±6 | 60.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,442 ±3.87 | 1,440 ±4 | 32.7% | 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
B Language: 繁體中文 1,411 [1,397–1,425] Percentile 66 · #76 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,467 ±9.68 | 1,427 ±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
C Language: Deutsch 1,380 [1,356–1,404] Percentile 46 · #78 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,398 ±16 | 1,400 ±14 | 89.7% | 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
B Language: English 1,416 [1,408–1,423] Percentile 70 · #83 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,439 ±3.69 | 1,430 ±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
B Language: Español 1,411 [1,390–1,431] Percentile 55 · #68 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,435 ±12 | 1,431 ±11 | 91.0% | 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
B Language: Français 1,411 [1,392–1,429] Percentile 52 · #65 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,447 ±11 | 1,430 ±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: Polski 1,396 [1,376–1,417] Percentile 42 · #76 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,410 ±14 | 1,416 ±12 | 90.9% | 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
B Language: Русский 1,403 [1,392–1,413] Percentile 62 · #90 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,411 ±6.51 | 1,417 ±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 |
|---|---|
| MiMo-V2-Omni | 1,406 B |
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.