MiniMax M2.1 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,380 ±3
Percentile 58 · #125 · provisional
People prefer / Solves tasks
1,391 / —
Human votes vs benchmarks, Elo-eq
Value
+18
$0.525 per 1M tokens, median of 19 providers · vendor $0.525
On your hardware
- GPU 12 GB #24 · UD-TQ1_0 · strong compression · ≈18 tok/s
- GPU 24 GB #27 · UD-IQ2_XXS · strong compression · ≈17 tok/s
- 128 GB unified memory #11 · Q3_K_M · ≈20 tok/s
Score decomposition
B General 1,380 [1,377–1,383] Percentile 58 · #125 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,392 ±2.59 | 1,392 ±3 | 26.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,410 ±3.35 | 1,404 ±3 | 26.0% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,399 ±4.41 | 1,412 ±4 | 12.6% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,431 ±8.64 | 1,420 ±7 | 11.1% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,416 ±4.45 | 1,415 ±4 | 6.3% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,396 ±5.65 | 1,395 ±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 1,388 [1,384–1,392] Percentile 61 · #108 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,384 ±4.85 | 1,417 ±1 | 46.8% | 2026-10-01 | — |
| LMArena |
text/coding
|
1,421 ±5.04 | 1,400 ±4 | 43.3% | 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 Math 1,362 [1,348–1,377] Percentile 50 · #128 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,396 ±9.10 | 1,389 ±9 | 85.7% | 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 1,386 [1,378–1,393] Percentile 58 · #112 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,362 ±5.71 | 1,389 ±6 | 60.9% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,416 ±4.45 | 1,415 ±4 | 32.6% | 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: 繁體中文 1,384 [1,373–1,396] Percentile 50 · #111 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,430 ±8.07 | 1,398 ±6 | 93.1% | 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
B Language: English 1,379 [1,371–1,386] Percentile 56 · #121 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,402 ±3.81 | 1,390 ±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
C Language: Español 1,376 [1,353–1,398] Percentile 32 · #102 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,396 ±14 | 1,395 ±13 | 90.3% | 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
C Language: Français 1,372 [1,349–1,396] Percentile 31 · #93 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,405 ±14 | 1,391 ±13 | 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
D Language: Polski 1,368 [1,348–1,387] Percentile 25 · #99 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/polish
|
1,372 ±13 | 1,383 ±11 | 91.4% | 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 Language: Русский 1,382 [1,372–1,392] Percentile 51 · #115 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,386 ±5.81 | 1,395 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| MiniMax M2.1 | 1,380 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.