qwen1.5-72b-chat in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,174 ±4
Percentile 21 · #232
People prefer / Solves tasks
1,172 / 1,181
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,174 [1,170–1,178] Percentile 21 · #232 · components: 7
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,166 ±2.65 | 1,166 ±3 | 22.2% | 2026-10-02 | — |
| LMArena |
text/hard_prompts
|
1,148 ±3.97 | 1,167 ±4 | 21.7% | 2026-10-02 | — |
| Epoch AI |
gpqa_diamond
decay ×0.26 |
0.29 ±0.02 | 1,174 ±9 | 15.3% | 2025-01-27 | — |
| LMArena |
text/instruction_following
|
1,141 ±3.73 | 1,168 ±4 | 10.8% | 2026-10-02 | — |
| LMArena |
text/expert
|
1,136 ±7.75 | 1,179 ±6 | 9.7% | 2026-10-02 | — |
| LMArena |
text/multi_turn
|
1,160 ±5.24 | 1,181 ±5 | 5.2% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,157 ±5.86 | 1,174 ±6 | 5.1% | 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
D Coding 1,175 [1,168–1,183] Percentile 19 · #226 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,165 ±4.86 | 1,172 ±4 | 89.9% | 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
D Math 1,171 [1,163–1,179] Percentile 20 · #205 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,164 ±4.93 | 1,166 ±5 | 87.9% | 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
D Writing 1,167 [1,160–1,174] Percentile 22 · #209 · components: 2 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,137 ±5.10 | 1,160 ±5 | 62.5% | 2026-10-02 | — |
| LMArena |
text/longer_query
|
1,157 ±5.86 | 1,174 ±6 | 30.9% | 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
D Language: 繁體中文 1,204 [1,195–1,213] Percentile 16 · #188 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/chinese
|
1,186 ±6.28 | 1,204 ±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: Deutsch 1,135 [1,119–1,151] Percentile 10 · #130 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/german
|
1,084 ±10 | 1,129 ±9 | 92.2% | 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: English 1,165 [1,159–1,171] Percentile 21 · #215 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,186 ±3.18 | 1,162 ±3 | 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
D Language: Español 1,138 [1,113–1,163] Percentile 5 · #142 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/spanish
|
1,110 ±15 | 1,130 ±14 | 89.4% | 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
D Language: Français 1,168 [1,147–1,189] Percentile 8 · #124 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/french
|
1,158 ±13 | 1,165 ±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: 日本語 1,176 [1,157–1,195] Percentile 9 · #117 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/japanese
|
1,061 ±14 | 1,174 ±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
D Language: 한국어 1,172 [1,152–1,191] Percentile 8 · #125 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/korean
|
1,049 ±14 | 1,169 ±11 | 91.3% | 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 Language: Русский 1,145 [1,134–1,156] Percentile 10 · #211 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/russian
|
1,104 ±6.52 | 1,141 ±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 |
|---|---|
| qwen1.5-72b-chat | 1,174 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.