reka-flash-21b-20240226-online in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,168 ±4
Percentile 20 · #235 · provisional
People prefer / Solves tasks
1,166 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,168 [1,164–1,172] Percentile 20 · #235 · components: 6 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,170 ±3.73 | 1,170 ±4 | 26.8% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,137 ±5.47 | 1,157 ±5 | 25.7% | 2026-10-02 | — |
| LMArena |
text/instruction_following
|
1,130 ±5.19 | 1,157 ±5 | 12.9% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,116 ±11 | 1,162 ±9 | 10.5% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,151 ±7.55 | 1,173 ±7 | 5.9% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,139 ±7.97 | 1,157 ±7 | 5.7% | 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
D Coding 1,175 [1,165–1,185] Percentile 18 · #227 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,165 ±6.48 | 1,171 ±6 | 89.3% | 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
D Math 1,175 [1,163–1,186] Percentile 20 · #203 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,168 ±6.99 | 1,170 ±7 | 87.0% | 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 Writing 1,158 [1,148–1,168] Percentile 20 · #215 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,131 ±7.31 | 1,153 ±8 | 61.8% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,139 ±7.97 | 1,157 ±7 | 31.0% | 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: 繁體中文 1,172 [1,161–1,183] Percentile 14 · #193 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,143 ±7.76 | 1,170 ±6 | 93.2% | 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
D Language: Deutsch 1,189 [1,168–1,210] Percentile 14 · #124 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,151 ±14 | 1,187 ±12 | 90.8% | 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
D Language: English 1,159 [1,150–1,168] Percentile 21 · #216 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,181 ±4.59 | 1,156 ±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
D Language: 한국어 1,209 [1,185–1,233] Percentile 10 · #123 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,104 ±18 | 1,210 ±14 | 89.8% | 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
D Language: Русский 1,195 [1,181–1,208] Percentile 14 · #202 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,163 ±8.17 | 1,194 ±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
History
The same in a table
| Model | 2026-10 |
|---|---|
| reka-flash-21b-20240226-online | 1,168 D |
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.