Mistral Medium 3.5 in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
B 1,386 ±8
Percentile 60 · #117
People prefer / Solves tasks
1,409 / 1,356
Human votes vs benchmarks, Elo-eq
Value
-19
$3 per 1M tokens, median of 7 providers
On your hardware
Does not fit the reference setups.
Score decomposition
B General 1,386 [1,378–1,393] Percentile 60 · #117 · components: 7
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| Epoch AI |
eci
|
141 ±1.18 | 1,370 ±9 | 40.9% | 2026-04-28 | — |
| LMArena |
text/overall
|
1,421 ±3.26 | 1,421 ±3 | 15.5% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,437 ±3.90 | 1,428 ±4 | 15.4% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,415 ±5.08 | 1,427 ±5 | 7.4% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,432 ±8.67 | 1,420 ±7 | 6.6% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,415 ±4.60 | 1,415 ±4 | 3.8% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,423 ±7.10 | 1,420 ±6 | 3.4% | 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 Coding 1,374 [1,371–1,378] Percentile 54 · #128 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
webdev/overall
|
1,263 ±7.53 | 1,382 ±2 | 59.7% | 2026-10-01 | — |
| LMArena |
text/coding
outlier |
1,461 ±5.47 | 1,436 ±5 | 27.6% | 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 Agents 1,377 [1,371–1,384] Percentile 2 · #57 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
agent/overall
|
-0.12 ±0.01 | 1,396 ±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 1,387 [1,367–1,406] Percentile 61 · #101 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,432 ±12 | 1,424 ±12 | 83.0% | 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
C Vision 1,394 [1,388–1,400] Percentile 44 · #64 · components: 3 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
vision/overall
|
1,222 ±4.85 | 1,404 ±4 | 63.9% | 2026-10-02 | — |
| LMArena |
vision/ocr
|
1,232 ±5.31 | 1,406 ±5 | 15.5% | 2026-10-02 | — |
| LMArena |
vision/diagram
|
1,254 ±8.16 | 1,422 ±7 | 14.0% | 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 Writing 1,392 [1,384–1,401] Percentile 62 · #103 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,374 ±6.98 | 1,402 ±7 | 59.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,415 ±4.60 | 1,415 ±4 | 33.7% | 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 1,391 [1,373–1,408] Percentile 52 · #107 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,442 ±12 | 1,407 ±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 1,409 [1,400–1,417] Percentile 67 · #91 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,433 ±4.31 | 1,423 ±5 | 93.6% | 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: Español 1,384 [1,358–1,409] Percentile 36 · #95 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,408 ±16 | 1,406 ±15 | 89.1% | 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: Français 1,408 [1,384–1,433] Percentile 51 · #67 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,450 ±15 | 1,432 ±14 | 89.6% | 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: Русский 1,388 [1,374–1,403] Percentile 55 · #105 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,396 ±8.70 | 1,403 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| Mistral Medium 3.5 | 1,386 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.