MiMo-V2.5 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,411 ±2
Percentile 73 · #79 · provisional
People prefer / Solves tasks
1,423 / —
Human votes vs benchmarks, Elo-eq
Value
+75
$0.175 per 1M tokens, median of 17 providers · vendor $0.175
On your hardware
- 128 GB unified memory #36 · UD-Q2_K_XL · strong compression · ≈23 tok/s
Score decomposition
B General 1,411 [1,409–1,413] Percentile 73 · #79 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,428 ±2.16 | 1,428 ±2 | 25.6% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,450 ±2.52 | 1,440 ±2 | 25.6% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,434 ±3.11 | 1,445 ±3 | 12.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,459 ±4.70 | 1,442 ±4 | 12.3% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,444 ±2.94 | 1,442 ±3 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,445 ±3.86 | 1,440 ±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
B Coding 1,415 [1,412–1,417] Percentile 74 · #72 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,438 ±3.06 | 1,432 ±1 | 46.0% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,469 ±3.31 | 1,443 ±3 | 44.4% | 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
B Math 1,399 [1,389–1,409] Percentile 70 · #78 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,436 ±6.20 | 1,428 ±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
B Vision 1,415 [1,411–1,418] Percentile 54 · #52 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,246 ±3.03 | 1,426 ±3 | 62.9% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,257 ±3.01 | 1,430 ±3 | 15.7% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,270 ±4.29 | 1,437 ±4 | 15.3% | 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
B Writing 1,414 [1,409–1,419] Percentile 72 · #76 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,393 ±3.96 | 1,421 ±4 | 61.7% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,444 ±2.94 | 1,442 ±3 | 32.0% | 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: 繁體中文 1,413 [1,404–1,422] Percentile 68 · #73 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,467 ±6.14 | 1,427 ±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
B Language: Deutsch 1,402 [1,385–1,419] Percentile 59 · #60 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,420 ±11 | 1,419 ±10 | 91.9% | 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: English 1,424 [1,418–1,429] Percentile 76 · #67 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,447 ±2.81 | 1,438 ±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
C Language: Español 1,396 [1,382–1,411] Percentile 45 · #83 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,414 ±8.52 | 1,412 ±8 | 92.6% | 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
B Language: Français 1,413 [1,400–1,426] Percentile 54 · #62 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,446 ±7.96 | 1,429 ±7 | 92.8% | 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
C Language: 日本語 1,342 [1,323–1,361] Percentile 28 · #92 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,304 ±14 | 1,355 ±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
C Language: 한국어 1,393 [1,378–1,408] Percentile 48 · #71 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,365 ±11 | 1,408 ±8 | 92.4% | 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: Polski 1,402 [1,387–1,417] Percentile 45 · #72 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,413 ±9.67 | 1,418 ±8 | 92.5% | 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
B Language: Русский 1,390 [1,382–1,397] Percentile 56 · #103 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,395 ±4.52 | 1,402 ±4 | 93.7% | 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
History
The same in a table
| Model | 2026-10 |
|---|---|
| MiMo-V2.5 | 1,411 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.