Llama 2 70B SteerLM Chat in fedi-index
The score in every slice, what it is made of, value, local run and history.
fedi-index · General
D 1,105 ±8
Percentile 12 · #262 · provisional
People prefer / Solves tasks
1,097 / —
Human votes vs benchmarks, Elo-eq
Value
—
On your hardware
Closed weights: cloud only.
Score decomposition
D General 1,105 [1,097–1,112] Percentile 12 · #262 · components: 4 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/overall
|
1,098 ±6.35 | 1,098 ±6 | 34.9% | 2026-11-11 | — |
| LMArena |
text/hard_prompts
|
1,047 ±10 | 1,076 ±9 | 29.6% | 2026-11-11 | — |
| LMArena |
text/instruction_following
|
1,060 ±9.14 | 1,091 ±9 | 15.4% | 2026-11-11 | — |
| LMArena |
text/multi_turn
|
1,058 ±14 | 1,088 ±13 | 5.9% | 2026-11-11 | — |
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 1,074 [1,054–1,095] Percentile 7 · #268 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/coding
|
1,025 ±14 | 1,047 ±13 | 82.3% | 2026-11-11 | — |
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 1,101 [1,080–1,122] Percentile 11 · #229 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/math
|
1,072 ±14 | 1,078 ±13 | 82.1% | 2026-11-11 | — |
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 1,121 [1,098–1,143] Percentile 14 · #226 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/creative_writing
|
1,090 ±12 | 1,112 ±13 | 90.3% | 2026-11-11 | — |
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 1,100 [1,087–1,114] Percentile 13 · #233 · components: 1 provisional
| Source | Component | Value | Elo-eq | Weight | Measured | Variant |
|---|---|---|---|---|---|---|
| LMArena |
text/english
|
1,120 ±6.99 | 1,092 ±7 | 92.8% | 2026-11-11 | — |
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 | 2026-11 |
|---|---|
| Llama 2 70B SteerLM Chat | 1,105 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.